BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Xingjun Ma

Xingjun Ma contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine LearningCryptography and SecurityArtificial IntelligenceComputation and LanguageDatabasesDistributed, Parallel, and Cluster ComputingSocial and Information NetworksSoftware EngineeringSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
36works
0followers
10topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

36 published item(s)

preprint2026arXiv

A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5

The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has driven major gains in reasoning, perception, and generation across language and vision, yet whether these advances translate into comparable improvements in safety remains unclear, partly due to fragmented evaluations that focus on isolated modalities or threat models. In this report, we present an integrated safety evaluation of six frontier models--GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5--assessing each across language, vision-language, and image generation using a unified protocol that combines benchmark, adversarial, multilingual, and compliance evaluations. By aggregating results into safety leaderboards and model profiles, we reveal a highly uneven safety landscape: while GPT-5.2 demonstrates consistently strong and balanced performance, other models exhibit clear trade-offs across benchmark safety, adversarial robustness, multilingual generalization, and regulatory compliance. Despite strong results under standard benchmarks, all models remain highly vulnerable under adversarial testing, with worst-case safety rates dropping below 6%. Text-to-image models show slightly stronger alignment in regulated visual risk categories, yet remain fragile when faced with adversarial or semantically ambiguous prompts. Overall, these findings highlight that safety in frontier models is inherently multidimensional--shaped by modality, language, and evaluation design--underscoring the need for standardized, holistic safety assessments to better reflect real-world risk and guide responsible deployment.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

AudioMosaic: Contrastive Masked Audio Representation Learning

Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generative reconstruction objectives, contrastive approaches remain less explored, partly due to the difficulty of designing effective audio augmentations and the large batch sizes required for contrastive pre-training. We introduce \textbf{AudioMosaic}, a contrastive learning-based audio encoder for general audio understanding. During pre-training, AudioMosaic constructs positive pairs by applying structured time-frequency masking to spectrogram patches, which reduces memory usage and enables efficient large-batch training. Compared with generative approaches, the AudioMosaic encoder learns more discriminative utterance-level representations that demonstrate strong transferability across datasets, domains, and acoustic conditions. Extensive experiments show that AudioMosaic achieves state-of-the-art performance on several standard audio benchmarks under both linear probing and fine-tuning. We further show that integrating the pretrained AudioMosaic encoder into audio-language models improves performance on audio-language tasks. The code is publicly available in our \href{https://github.com/HanxunH/AudioMosaic}{GitHub repository}.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents

Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables autonomy, it also expands the attack surface for backdoor threats. Backdoor triggers injected into specific stages of an agent workflow can persist through multiple intermediate states and adversely influence downstream outputs. However, existing studies remain fragmented and typically analyze individual attack vectors in isolation, leaving the cross-stage interaction and propagation of backdoor triggers poorly understood from an agent-centric perspective. To fill this gap, we propose \textbf{BackdoorAgent}, a modular and stage-aware framework that provides a unified, agent-centric view of backdoor threats in LLM agents. BackdoorAgent structures the attack surface into three functional stages of agentic workflows, including \textbf{planning attacks}, \textbf{memory attacks}, and \textbf{tool-use attacks}, and instruments agent execution to enable systematic analysis of trigger activation and propagation across different stages. Building on this framework, we construct a standardized benchmark spanning four representative agent applications: \textbf{Agent QA}, \textbf{Agent Code}, \textbf{Agent Web}, and \textbf{Agent Drive}, covering both language-only and multimodal settings. Our empirical analysis shows that \textit{triggers implanted at a single stage can persist across multiple steps and propagate through intermediate states.} For instance, when using a GPT-based backbone, we observe trigger persistence in 43.58\% of planning attacks, 77.97\% of memory attacks, and 60.28\% of tool-stage attacks, highlighting the vulnerabilities of the agentic workflow itself to backdoor threats. To facilitate reproducibility and future research, our code and benchmark are publicly available at GitHub.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single, predefined objectives, tightly coupling each attack to a specific model or task, which restricts their scalability and flexibility in real-world scenarios. In this work, we present DarkLLM, a novel attack framework that trains an LLM to translate natural-language attack instructions into latent attack vectors, which are then decoded into visual adversarial perturbations. By leveraging natural-language instruction tuning, DarkLLM not only unifies targeted, untargeted, segmentation, and multi-model attacks within a single framework, but also achieves flexible and controllable adversarial generation, enabling each instruction to produce a perturbation that induces desired behaviors across heterogeneous models. Through extensive experiments across 4 tasks, 13 datasets, and 15 models, we demonstrate that DarkLLM with only 1B parameters can follow attacker instructions and generate highly effective attacks against CLIP, SAM, and frontier LLMs, revealing a systemic vulnerability in modern foundation models.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

ImageAttributionBench: How Far Are We from Generalizable Attribution?

The rapid advancement of generative AI has enabled the creation of highly realistic and diverse synthetic images, posing critical challenges for image provenance and misinformation detection. This underscores the urgent need for effective image attribution. However, existing attribution datasets are constrained by limited scale, outdated generation methods, and insufficient semantic diversity - hindering the development of robust and generalizable attribution models. To address these limitations, we introduce ImageAttributionBench, a comprehensive dataset comprising images synthesized by a wide array of advanced generative models with state-of-the-art (SOTA) architectures. Covering multiple real-world semantic domains, the dataset offers rich diversity and scale to support and accelerate progress in image attribution research. To simulate real-world attribution scenarios, we evaluate several SOTA attribution methods on ImageAttributionBench under two challenging settings: (1) training on a standard balanced split and testing on degraded images, and (2) training and testing on semantically disjoint splits. In both cases, current methods exhibit consistently poor performance, revealing significant limitations in their robustness and generalization to unseen semantic content. Our work provides a rigorous benchmark to facilitate the development and evaluation of future image attribution methods.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models

As Large Language Models (LLMs) are increasingly deployed in cross-linguistic contexts, ensuring safety in diverse regulatory and cultural environments has become a critical challenge. However, existing multilingual benchmarks largely rely on general risk taxonomies and machine translation, which confines guardrail models to these predefined categories and hinders their ability to align with region-specific regulations and cultural nuances. To bridge these gaps, we introduce ML-Bench, a policy-grounded multilingual safety benchmark covering 14 languages. ML-Bench is constructed directly from regional regulations, where risk categories and fine-grained rules derived from jurisdiction-specific legal texts are directly used to guide the generation of multilingual safety data, enabling culturally and legally aligned evaluation across languages. Building on ML-Bench, we develop ML-Guard, a Diffusion Large Language Model (dLLM)-based guardrail model that supports multilingual safety judgment and policy-conditioned compliance assessment. ML-Guard has two variants, one 1.5B lightweight model for fast `safe/unsafe' checking and a more capable 7B model for customized compliance checking with detailed explanations. We conduct extensive experiments against 11 strong guardrail baselines across 6 existing multilingual safety benchmarks and our ML-Bench, and show that ML-Guard consistently outperforms prior methods. We hope that ML-Bench and ML-Guard can help advance the development of regulation-aware and culturally aligned multilingual guardrail systems.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models

The widespread practice of fine-tuning open-source Vision-Language Models (VLMs) raises a critical security concern: jailbreak vulnerabilities in base models may persist in downstream variants, enabling transferable attacks across fine-tuned systems. To investigate this risk, we propose the Simulated Ensemble Attack (SEA), a grey-box jailbreak framework that assumes full access to the base VLM but no knowledge of the fine-tuned target. SEA enhances transferability via Fine-tuning Trajectory Simulation (FTS), which models bounded parameter variations in the vision encoder, and Targeted Prompt Guidance (TPG), which stabilizes adversarial optimization through auxiliary textual guidance. Experiments on the Qwen2-VL family demonstrate that SEA achieves consistently high transfer success and toxicity rates across diverse fine-tuned variants, including safety-enhanced models, while standard PGD-based image jailbreaks exhibit negligible transferability. Further analysis reveals that fine-tuning primarily induces localized parameter shifts around the base model, explaining why attacks optimized over a simulated neighborhood transfer effectively. We also show that SEA generalizes across different base generations (e.g., Qwen2.5/3-VL), indicating that its effectiveness arises from shared fine-tuning-induced behaviors rather than architecture- or initialization-specific factors.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models

Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world deployment. To enhance robustness without requiring downstream task-specific retraining, we propose TAME, a novel test-time defense. Building upon our prior Test-Time Adversarial Prompt Tuning (TAPT), TAME introduces an architectural reformulation by replacing TAPT's single adaptive prompt with an input-conditioned Mixture-of-Experts (MoE) framework, enabling more expressive and adaptive defense. Specifically, TAME maintains a bank of learnable expert prompts and employs an input-dependent routing mechanism to aggregate a customized prompt mixture for each unlabeled test sample at inference time. This test-time defense mechanism is driven by three unsupervised objectives: (1) multi-view prediction entropy minimization, (2) layer-wise alignment of visual token statistics to precomputed clean and adversarial reference distributions, and (3) MoE regularization for balanced expert utilization and prompt diversity. We evaluated TAME on 11 benchmark datasets, including ImageNet and 10 additional zero-shot datasets. The results show that TAME improves the zero-shot adversarial robustness of the original CLIP by at least 49.1% under AutoAttack while largely preserving generalization on clean samples. TAME also consistently outperforms existing adversarial prompt tuning methods across multiple prompt designs, yielding an average robustness gain of at least 30.2%.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models

Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively underexplored. In this paper, we take a training-free perspective and introduce ViSRA, a human-aligned Video-based Spatial Reasoning Agent, as a framework to probe the spatial reasoning mechanism of MLLMs. ViSRA elicits spatial reasoning in a modular and extensible manner by leveraging explicit spatial information from expert models, enabling a plug-and-play flexible paradigm. ViSRA offers two key advantages: (1) human-aligned and transferable 3D understanding rather than task-specific overfitting; and (2) no post-training computational cost along with heavy manual curation of spatial reasoning datasets. Experimental results demonstrate consistent improvement across a set of MLLMs on both existing benchmarks and unseen 3D spatial reasoning tasks, with ViSRA outperforming baselines by up to a 15.6% and 28.9% absolute margin respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

End-to-End Anti-Backdoor Learning on Images and Time Series

Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security. These attacks manipulate model behavior by embedding a hidden trigger during the training phase, allowing unauthorized control over the model's output during inference time. Although numerous defenses exist for image classification models, there is a conspicuous absence of defenses tailored for time series data, as well as an end-to-end solution capable of training clean models on poisoned data. To address this gap, this paper builds upon Anti-Backdoor Learning (ABL) and introduces an innovative method, End-to-End Anti-Backdoor Learning (E2ABL), for robust training against backdoor attacks. Unlike the original ABL, which employs a two-stage training procedure, E2ABL accomplishes end-to-end training through an additional classification head linked to the shallow layers of a Deep Neural Network (DNN). This secondary head actively identifies potential backdoor triggers, allowing the model to dynamically cleanse these samples and their corresponding labels during training. Our experiments reveal that E2ABL significantly improves on existing defenses and is effective against a broad range of backdoor attacks in both image and time series domains.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss and its variants. In this paper, we generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regularization term with a single power parameter $α$. We call this new family of losses the $α$-IoU losses and analyze properties such as order preservingness and loss/gradient reweighting. Experiments on multiple object detection benchmarks and models demonstrate that $α$-IoU losses, 1) can surpass existing IoU-based losses by a noticeable performance margin; 2) offer detectors more flexibility in achieving different levels of bbox regression accuracy by modulating $α$; and 3) are more robust to small datasets and noisy bboxes.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Backdoor Attacks on Crowd Counting

Crowd counting is a regression task that estimates the number of people in a scene image, which plays a vital role in a range of safety-critical applications, such as video surveillance, traffic monitoring and flow control. In this paper, we investigate the vulnerability of deep learning based crowd counting models to backdoor attacks, a major security threat to deep learning. A backdoor attack implants a backdoor trigger into a target model via data poisoning so as to control the model's predictions at test time. Different from image classification models on which most of existing backdoor attacks have been developed and tested, crowd counting models are regression models that output multi-dimensional density maps, thus requiring different techniques to manipulate. In this paper, we propose two novel Density Manipulation Backdoor Attacks (DMBA$^{-}$ and DMBA$^{+}$) to attack the model to produce arbitrarily large or small density estimations. Experimental results demonstrate the effectiveness of our DMBA attacks on five classic crowd counting models and four types of datasets. We also provide an in-depth analysis of the unique challenges of backdooring crowd counting models and reveal two key elements of effective attacks: 1) full and dense triggers and 2) manipulation of the ground truth counts or density maps. Our work could help evaluate the vulnerability of crowd counting models to potential backdoor attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of defense methods have been proposed to train adversarially robust DNNs, among which adversarial training has demonstrated promising results. However, despite preliminary understandings developed for adversarial training, it is still not clear, from the architectural perspective, what configurations can lead to more robust DNNs. In this paper, we address this gap via a comprehensive investigation on the impact of network width and depth on the robustness of adversarially trained DNNs. Specifically, we make the following key observations: 1) more parameters (higher model capacity) does not necessarily help adversarial robustness; 2) reducing capacity at the last stage (the last group of blocks) of the network can actually improve adversarial robustness; and 3) under the same parameter budget, there exists an optimal architectural configuration for adversarial robustness. We also provide a theoretical analysis explaning why such network configuration can help robustness. These architectural insights can help design adversarially robust DNNs. Code is available at \url{https://github.com/HanxunH/RobustWRN}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Few-Shot Backdoor Attacks on Visual Object Tracking

Visual object tracking (VOT) has been widely adopted in mission-critical applications, such as autonomous driving and intelligent surveillance systems. In current practice, third-party resources such as datasets, backbone networks, and training platforms are frequently used to train high-performance VOT models. Whilst these resources bring certain convenience, they also introduce new security threats into VOT models. In this paper, we reveal such a threat where an adversary can easily implant hidden backdoors into VOT models by tempering with the training process. Specifically, we propose a simple yet effective few-shot backdoor attack (FSBA) that optimizes two losses alternately: 1) a \emph{feature loss} defined in the hidden feature space, and 2) the standard \emph{tracking loss}. We show that, once the backdoor is embedded into the target model by our FSBA, it can trick the model to lose track of specific objects even when the \emph{trigger} only appears in one or a few frames. We examine our attack in both digital and physical-world settings and show that it can significantly degrade the performance of state-of-the-art VOT trackers. We also show that our attack is resistant to potential defenses, highlighting the vulnerability of VOT models to potential backdoor attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Finding Influentials in Twitter: A Temporal Influence Ranking Model

With the growing popularity of online social media, identifying influential users in these social networks has become very popular. Existing works have studied user attributes, network structure and user interactions when measuring user influence. In contrast to these works, we focus on user behavioural characteristics. We investigate the temporal dynamics of user activity patterns and how these patterns affect user interactions. We assimilate such characteristics into a PageRank based temporal influence ranking model (TIR) to identify influential users. The transition probability in TIR is predicted by a logistic regression model and the random walk, biased according to users' temporal activity patterns. Experiments demonstrate that TIR has better performance and is more stable than the existing models in global influence ranking and friend recommendation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Improving Adversarial Robustness via Channel-wise Activation Suppressing

The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs). Different from existing works, in this paper, we highlight two new characteristics of adversarial examples from the channel-wise activation perspective: 1) the activation magnitudes of adversarial examples are higher than that of natural examples; and 2) the channels are activated more uniformly by adversarial examples than natural examples. We find that the state-of-the-art defense adversarial training has addressed the first issue of high activation magnitudes via training on adversarial examples, while the second issue of uniform activation remains. This motivates us to suppress redundant activation from being activated by adversarial perturbations via a Channel-wise Activation Suppressing (CAS) strategy. We show that CAS can train a model that inherently suppresses adversarial activation, and can be easily applied to existing defense methods to further improve their robustness. Our work provides a simple but generic training strategy for robustifying the intermediate layer activation of DNNs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On the Convergence and Robustness of Adversarial Training

Improving the robustness of deep neural networks (DNNs) to adversarial examples is an important yet challenging problem for secure deep learning. Across existing defense techniques, adversarial training with Projected Gradient Decent (PGD) is amongst the most effective. Adversarial training solves a min-max optimization problem, with the \textit{inner maximization} generating adversarial examples by maximizing the classification loss, and the \textit{outer minimization} finding model parameters by minimizing the loss on adversarial examples generated from the inner maximization. A criterion that measures how well the inner maximization is solved is therefore crucial for adversarial training. In this paper, we propose such a criterion, namely First-Order Stationary Condition for constrained optimization (FOSC), to quantitatively evaluate the convergence quality of adversarial examples found in the inner maximization. With FOSC, we find that to ensure better robustness, it is essential to use adversarial examples with better convergence quality at the \textit{later stages} of training. Yet at the early stages, high convergence quality adversarial examples are not necessary and may even lead to poor robustness. Based on these observations, we propose a \textit{dynamic} training strategy to gradually increase the convergence quality of the generated adversarial examples, which significantly improves the robustness of adversarial training. Our theoretical and empirical results show the effectiveness of the proposed method.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Practical Privacy Attacks on Vertical Federated Learning

Federated learning (FL) is a privacy-preserving learning paradigm that allows multiple parities to jointly train a powerful machine learning model without sharing their private data. According to the form of collaboration, FL can be further divided into horizontal federated learning (HFL) and vertical federated learning (VFL). In HFL, participants share the same feature space and collaborate on data samples, while in VFL, participants share the same sample IDs and collaborate on features. VFL has a broader scope of applications and is arguably more suitable for joint model training between large enterprises. In this paper, we focus on VFL and investigate potential privacy leakage in real-world VFL frameworks. We design and implement two practical privacy attacks: reverse multiplication attack for the logistic regression VFL protocol; and reverse sum attack for the XGBoost VFL protocol. We empirically show that the two attacks are (1) effective - the adversary can successfully steal the private training data, even when the intermediate outputs are encrypted to protect data privacy; (2) evasive - the attacks do not deviate from the protocol specification nor deteriorate the accuracy of the target model; and (3) easy - the adversary needs little prior knowledge about the data distribution of the target participant. We also show the leaked information is as effective as the raw training data in training an alternative classifier. We further discuss potential countermeasures and their challenges, which we hope can lead to several promising research directions.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Privacy and Robustness in Federated Learning: Attacks and Defenses

As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol design has been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy-preserving federated learning.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

VeriFi: Towards Verifiable Federated Unlearning

Federated learning (FL) is a collaborative learning paradigm where participants jointly train a powerful model without sharing their private data. One desirable property for FL is the implementation of the right to be forgotten (RTBF), i.e., a leaving participant has the right to request to delete its private data from the global model. However, unlearning itself may not be enough to implement RTBF unless the unlearning effect can be independently verified, an important aspect that has been overlooked in the current literature. In this paper, we prompt the concept of verifiable federated unlearning, and propose VeriFi, a unified framework integrating federated unlearning and verification that allows systematic analysis of the unlearning and quantification of its effect, with different combinations of multiple unlearning and verification methods. In VeriFi, the leaving participant is granted the right to verify (RTV), that is, the participant notifies the server before leaving, then actively verifies the unlearning effect in the next few communication rounds. The unlearning is done at the server side immediately after receiving the leaving notification, while the verification is done locally by the leaving participant via two steps: marking (injecting carefully-designed markers to fingerprint the leaver) and checking (examining the change of the global model's performance on the markers). Based on VeriFi, we conduct the first systematic and large-scale study for verifiable federated unlearning, considering 7 unlearning methods and 5 verification methods. Particularly, we propose a more efficient and FL-friendly unlearning method, and two more effective and robust non-invasive-verification methods. We extensively evaluate VeriFi on 7 datasets and 4 types of deep learning models. Our analysis establishes important empirical understandings for more trustworthy federated unlearning.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

A Lazy Approach for Efficient Index Learning

Learned indices using neural networks have been shown to outperform traditional indices such as B-trees in both query time and memory. However, learning the distribution of a large dataset can be expensive, and updating learned indices is difficult, thus hindering their usage in practical applications. In this paper, we address the efficiency and update issues of learned indices through agile model reuse. We pre-train learned indices over a set of synthetic (rather than real) datasets and propose a novel approach to reuse these pre-trained models for a new (real) dataset. The synthetic datasets are created to cover a large range of different distributions. Given a new dataset DT, we select the learned index of a synthetic dataset similar to DT, to index DT. We show a bound over the indexing error when a pre-trained index is selected. We further show how our techniques can handle data updates and bound the resultant indexing errors. Experimental results on synthetic and real datasets confirm the effectiveness and efficiency of our proposed lazy (model reuse) approach.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Adversarial Interaction Attack: Fooling AI to Misinterpret Human Intentions

Understanding the actions of both humans and artificial intelligence (AI) agents is important before modern AI systems can be fully integrated into our daily life. In this paper, we show that, despite their current huge success, deep learning based AI systems can be easily fooled by subtle adversarial noise to misinterpret the intention of an action in interaction scenarios. Based on a case study of skeleton-based human interactions, we propose a novel adversarial attack on interactions, and demonstrate how DNN-based interaction models can be tricked to predict the participants' reactions in unexpected ways. From a broader perspective, the scope of our proposed attack method is not confined to problems related to skeleton data but can also be extended to any type of problems involving sequential regressions. Our study highlights potential risks in the interaction loop with AI and humans, which need to be carefully addressed when deploying AI systems in safety-critical applications.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks

Electrocardiogram (ECG) acquisition requires an automated system and analysis pipeline for understanding specific rhythm irregularities. Deep neural networks have become a popular technique for tracing ECG signals, outperforming human experts. Despite this, convolutional neural networks are susceptible to adversarial examples that can misclassify ECG signals and decrease the model's precision. Moreover, they do not generalize well on the out-of-distribution dataset. The GAN architecture has been employed in recent works to synthesize adversarial ECG signals to increase existing training data. However, they use a disjointed CNN-based classification architecture to detect arrhythmia. Till now, no versatile architecture has been proposed that can detect adversarial examples and classify arrhythmia simultaneously. To alleviate this, we propose a novel Conditional Generative Adversarial Network to simultaneously generate ECG signals for different categories and detect cardiac abnormalities. Moreover, the model is conditioned on class-specific ECG signals to synthesize realistic adversarial examples. Consequently, we compare our architecture and show how it outperforms other classification models in normal/abnormal ECG signal detection by benchmarking real world and adversarial signals.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

Deep neural networks (DNNs) are known vulnerable to backdoor attacks, a training time attack that injects a trigger pattern into a small proportion of training data so as to control the model's prediction at the test time. Backdoor attacks are notably dangerous since they do not affect the model's performance on clean examples, yet can fool the model to make incorrect prediction whenever the trigger pattern appears during testing. In this paper, we propose a novel defense framework Neural Attention Distillation (NAD) to erase backdoor triggers from backdoored DNNs. NAD utilizes a teacher network to guide the finetuning of the backdoored student network on a small clean subset of data such that the intermediate-layer attention of the student network aligns with that of the teacher network. The teacher network can be obtained by an independent finetuning process on the same clean subset. We empirically show, against 6 state-of-the-art backdoor attacks, NAD can effectively erase the backdoor triggers using only 5\% clean training data without causing obvious performance degradation on clean examples. Code is available in https://github.com/bboylyg/NAD.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

RobOT: Robustness-Oriented Testing for Deep Learning Systems

Recently, there has been a significant growth of interest in applying software engineering techniques for the quality assurance of deep learning (DL) systems. One popular direction is deep learning testing, where adversarial examples (a.k.a.~bugs) of DL systems are found either by fuzzing or guided search with the help of certain testing metrics. However, recent studies have revealed that the commonly used neuron coverage metrics by existing DL testing approaches are not correlated to model robustness. It is also not an effective measurement on the confidence of the model robustness after testing. In this work, we address this gap by proposing a novel testing framework called Robustness-Oriented Testing (RobOT). A key part of RobOT is a quantitative measurement on 1) the value of each test case in improving model robustness (often via retraining), and 2) the convergence quality of the model robustness improvement. RobOT utilizes the proposed metric to automatically generate test cases valuable for improving model robustness. The proposed metric is also a strong indicator on how well robustness improvement has converged through testing. Experiments on multiple benchmark datasets confirm the effectiveness and efficiency of RobOT in improving DL model robustness, with 67.02% increase on the adversarial robustness that is 50.65% higher than the state-of-the-art work DeepGini.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Unlearnable Examples: Making Personal Data Unexploitable

The volume of "free" data on the internet has been key to the current success of deep learning. However, it also raises privacy concerns about the unauthorized exploitation of personal data for training commercial models. It is thus crucial to develop methods to prevent unauthorized data exploitation. This paper raises the question: \emph{can data be made unlearnable for deep learning models?} We present a type of \emph{error-minimizing} noise that can indeed make training examples unlearnable. Error-minimizing noise is intentionally generated to reduce the error of one or more of the training example(s) close to zero, which can trick the model into believing there is "nothing" to learn from these example(s). The noise is restricted to be imperceptible to human eyes, and thus does not affect normal data utility. We empirically verify the effectiveness of error-minimizing noise in both sample-wise and class-wise forms. We also demonstrate its flexibility under extensive experimental settings and practicability in a case study of face recognition. Our work establishes an important first step towards making personal data unexploitable to deep learning models.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space

Deep neural networks (DNNs) are increasingly deployed in different applications to achieve state-of-the-art performance. However, they are often applied as a black box with limited understanding of what knowledge the model has learned from the data. In this paper, we focus on image classification and propose a method to visualize and understand the class-wise knowledge (patterns) learned by DNNs under three different settings including natural, backdoor and adversarial. Different to existing visualization methods, our method searches for a single predictive pattern in the pixel space to represent the knowledge learned by the model for each class. Based on the proposed method, we show that DNNs trained on natural (clean) data learn abstract shapes along with some texture, and backdoored models learn a suspicious pattern for the backdoored class. Interestingly, the phenomenon that DNNs can learn a single predictive pattern for each class indicates that DNNs can learn a backdoor even from clean data, and the pattern itself is a backdoor trigger. In the adversarial setting, we show that adversarially trained models tend to learn more simplified shape patterns. Our method can serve as a useful tool to better understand the knowledge learned by DNNs on different datasets under different settings.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. Existing works have mostly focused on either digital adversarial examples created via small and imperceptible perturbations, or physical-world adversarial examples created with large and less realistic distortions that are easily identified by human observers. In this paper, we propose a novel approach, called Adversarial Camouflage (\emph{AdvCam}), to craft and camouflage physical-world adversarial examples into natural styles that appear legitimate to human observers. Specifically, \emph{AdvCam} transfers large adversarial perturbations into customized styles, which are then "hidden" on-target object or off-target background. Experimental evaluation shows that, in both digital and physical-world scenarios, adversarial examples crafted by \emph{AdvCam} are well camouflaged and highly stealthy, while remaining effective in fooling state-of-the-art DNN image classifiers. Hence, \emph{AdvCam} is a flexible approach that can help craft stealthy attacks to evaluate the robustness of DNNs. \emph{AdvCam} can also be used to protect private information from being detected by deep learning systems.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Clean-Label Backdoor Attacks on Video Recognition Models

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target class for any test examples that contain the trigger pattern. As such, backdoor attacks are hard to detect, and have raised severe security concerns in real-world applications. Thus far, backdoor research has mostly been conducted in the image domain with image classification models. In this paper, we show that existing image backdoor attacks are far less effective on videos, and outline 4 strict conditions where existing attacks are likely to fail: 1) scenarios with more input dimensions (eg. videos), 2) scenarios with high resolution, 3) scenarios with a large number of classes and few examples per class (a "sparse dataset"), and 4) attacks with access to correct labels (eg. clean-label attacks). We propose the use of a universal adversarial trigger as the backdoor trigger to attack video recognition models, a situation where backdoor attacks are likely to be challenged by the above 4 strict conditions. We show on benchmark video datasets that our proposed backdoor attack can manipulate state-of-the-art video models with high success rates by poisoning only a small proportion of training data (without changing the labels). We also show that our proposed backdoor attack is resistant to state-of-the-art backdoor defense/detection methods, and can even be applied to improve image backdoor attacks. Our proposed video backdoor attack not only serves as a strong baseline for improving the robustness of video models, but also provides a new perspective for more understanding more powerful backdoor attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Generative Image Inpainting with Submanifold Alignment

Image inpainting aims at restoring missing regions of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based generative inpainting models do not explicitly exploit the structural or textural consistency between restored contents and their surrounding contexts.To address this limitation, we propose to enforce the alignment (or closeness) between the local data submanifolds (or subspaces) around restored images and those around the original (uncorrupted) images during the learning process of GAN-based inpainting models. We exploit Local Intrinsic Dimensionality (LID) to measure, in deep feature space, the alignment between data submanifolds learned by a GAN model and those of the original data, from a perspective of both images (denoted as iLID) and local patches (denoted as pLID) of images. We then apply iLID and pLID as regularizations for GAN-based inpainting models to encourage two levels of submanifold alignment: 1) an image-level alignment for improving structural consistency, and 2) a patch-level alignment for improving textural details. Experimental results on four benchmark datasets show that our proposed model can generate more accurate results than state-of-the-art models.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning

This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy. A novel reputation system is proposed through digital tokens and local credibility to ensure fairness, in combination with differential privacy to guarantee privacy. In particular, we build a fair and differentially private decentralised deep learning framework called FDPDDL, which enables parties to derive more accurate local models in a fair and private manner by using our developed two-stage scheme: during the initialisation stage, artificial samples generated by Differentially Private Generative Adversarial Network (DPGAN) are used to mutually benchmark the local credibility of each party and generate initial tokens; during the update stage, Differentially Private SGD (DPSGD) is used to facilitate collaborative privacy-preserving deep learning, and local credibility and tokens of each party are updated according to the quality and quantity of individually released gradients. Experimental results on benchmark datasets under three realistic settings demonstrate that FDPDDL achieves high fairness, yields comparable accuracy to the centralised and distributed frameworks, and delivers better accuracy than the standalone framework.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Normalized Loss Functions for Deep Learning with Noisy Labels

Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross Entropy (CE) loss is not robust to noisy labels. Whilst new loss functions have been designed, they are only partially robust. In this paper, we theoretically show by applying a simple normalization that: any loss can be made robust to noisy labels. However, in practice, simply being robust is not sufficient for a loss function to train accurate DNNs. By investigating several robust loss functions, we find that they suffer from a problem of underfitting. To address this, we propose a framework to build robust loss functions called Active Passive Loss (APL). APL combines two robust loss functions that mutually boost each other. Experiments on benchmark datasets demonstrate that the family of new loss functions created by our APL framework can consistently outperform state-of-the-art methods by large margins, especially under large noise rates such as 60% or 80% incorrect labels.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data. At test time, the victim model behaves normally on clean test data, yet consistently predicts a specific (likely incorrect) target class whenever the backdoor pattern is present in a test example. While existing backdoor attacks are effective, they are not stealthy. The modifications made on training data or labels are often suspicious and can be easily detected by simple data filtering or human inspection. In this paper, we present a new type of backdoor attack inspired by an important natural phenomenon: reflection. Using mathematical modeling of physical reflection models, we propose reflection backdoor (Refool) to plant reflections as backdoor into a victim model. We demonstrate on 3 computer vision tasks and 5 datasets that, Refool can attack state-of-the-art DNNs with high success rate, and is resistant to state-of-the-art backdoor defenses.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Short-Term and Long-Term Context Aggregation Network for Video Inpainting

Video inpainting aims to restore missing regions of a video and has many applications such as video editing and object removal. However, existing methods either suffer from inaccurate short-term context aggregation or rarely explore long-term frame information. In this work, we present a novel context aggregation network to effectively exploit both short-term and long-term frame information for video inpainting. In the encoding stage, we propose boundary-aware short-term context aggregation, which aligns and aggregates, from neighbor frames, local regions that are closely related to the boundary context of missing regions into the target frame. Furthermore, we propose dynamic long-term context aggregation to globally refine the feature map generated in the encoding stage using long-term frame features, which are dynamically updated throughout the inpainting process. Experiments show that it outperforms state-of-the-art methods with better inpainting results and fast inpainting speed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

Skip connections are an essential component of current state-of-the-art deep neural networks (DNNs) such as ResNet, WideResNet, DenseNet, and ResNeXt. Despite their huge success in building deeper and more powerful DNNs, we identify a surprising security weakness of skip connections in this paper. Use of skip connections allows easier generation of highly transferable adversarial examples. Specifically, in ResNet-like (with skip connections) neural networks, gradients can backpropagate through either skip connections or residual modules. We find that using more gradients from the skip connections rather than the residual modules according to a decay factor, allows one to craft adversarial examples with high transferability. Our method is termed Skip Gradient Method(SGM). We conduct comprehensive transfer attacks against state-of-the-art DNNs including ResNets, DenseNets, Inceptions, Inception-ResNet, Squeeze-and-Excitation Network (SENet) and robustly trained DNNs. We show that employing SGM on the gradient flow can greatly improve the transferability of crafted attacks in almost all cases. Furthermore, SGM can be easily combined with existing black-box attack techniques, and obtain high improvements over state-of-the-art transferability methods. Our findings not only motivate new research into the architectural vulnerability of DNNs, but also open up further challenges for the design of secure DNN architectures.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Fair and Privacy-Preserving Federated Deep Models

The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggregate local model updates. Server-based solutions are prone to the problem of a single-point-of-failure. In this respect, collaborative learning frameworks, such as federated learning (FL), are more robust. Existing federated learning frameworks overlook an important aspect of participation: fairness. All parties are given the same final model without regard to their contributions. To address these issues, we propose a decentralized Fair and Privacy-Preserving Deep Learning (FPPDL) framework to incorporate fairness into federated deep learning models. In particular, we design a local credibility mutual evaluation mechanism to guarantee fairness, and a three-layer onion-style encryption scheme to guarantee both accuracy and privacy. Different from existing FL paradigm, under FPPDL, each participant receives a different version of the FL model with performance commensurate with his contributions. Experiments on benchmark datasets demonstrate that FPPDL balances fairness, privacy and accuracy. It enables federated learning ecosystems to detect and isolate low-contribution parties, thereby promoting responsible participation.

0 citations0 reviewsNo code linkedOpen access