Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
22works
0followers
21topics
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

22 published item(s)

preprint2026arXiv

A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion

We present A-CODE, a fully atomic unified one-stage protein co-design model that simultaneously refines discrete atom types and continuous atom coordinates. Unlike predominant two-stage methods that cascade structure design with amino acid-level sequence design, our approach is fully atomic within a unified multimodal diffusion framework, in which residue identities are inferred solely from atom-level predictions. Built upon the powerful all-atom architecture, A-CODE achieves superior designability for unconditional protein generation, outperforming all existing one-stage and two-stage design models. For binder design, A-CODE rivals and even outperforms existing state-of-the-art two-stage design models and, compared with the existing one-stage co-design model, achieves a drastic tenfold improvement in success rate on hard tasks. The inherent flexibility of our atomic formulation enables, for the first time, seamless adaptation to non-canonical amino acid (ncAA) modeling. Our fully atomic framework establishes a new, versatile foundation for all-atom generative modeling that can be naturally extended to complex biomolecular systems.

preprint2022arXiv

AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis

Deep neural networks (DNNs) are proved to be vulnerable against backdoor attacks. A backdoor is often embedded in the target DNNs through injecting a backdoor trigger into training examples, which can cause the target DNNs misclassify an input attached with the backdoor trigger. Existing backdoor detection methods often require the access to the original poisoned training data, the parameters of the target DNNs, or the predictive confidence for each given input, which are impractical in many real-world applications, e.g., on-device deployed DNNs. We address the black-box hard-label backdoor detection problem where the DNN is fully black-box and only its final output label is accessible. We approach this problem from the optimization perspective and show that the objective of backdoor detection is bounded by an adversarial objective. Further theoretical and empirical studies reveal that this adversarial objective leads to a solution with highly skewed distribution; a singularity is often observed in the adversarial map of a backdoor-infected example, which we call the adversarial singularity phenomenon. Based on this observation, we propose the adversarial extreme value analysis(AEVA) to detect backdoors in black-box neural networks. AEVA is based on an extreme value analysis of the adversarial map, computed from the monte-carlo gradient estimation. Evidenced by extensive experiments across multiple popular tasks and backdoor attacks, our approach is shown effective in detecting backdoor attacks under the black-box hard-label scenarios.

preprint2022arXiv

Brief Industry Paper: The Necessity of Adaptive Data Fusion in Infrastructure-Augmented Autonomous Driving System

This paper is the first to provide a thorough system design overview along with the fusion methods selection criteria of a real-world cooperative autonomous driving system, named Infrastructure-Augmented Autonomous Driving or IAAD. We present an in-depth introduction of the IAAD hardware and software on both road-side and vehicle-side computing and communication platforms. We extensively characterize the IAAD system in the context of real-world deployment scenarios and observe that the network condition that fluctuates along the road is currently the main technical roadblock for cooperative autonomous driving. To address this challenge, we propose new fusion methods, dubbed "inter-frame fusion" and "planning fusion" to complement the current state-of-the-art "intra-frame fusion". We demonstrate that each fusion method has its own benefit and constraint.

preprint2022arXiv

Deep Partial Updating: Towards Communication Efficient Updating for On-device Inference

Emerging edge intelligence applications require the server to retrain and update deep neural networks deployed on remote edge nodes to leverage newly collected data samples. Unfortunately, it may be impossible in practice to continuously send fully updated weights to these edge nodes due to the highly constrained communication resource. In this paper, we propose the weight-wise deep partial updating paradigm, which smartly selects a small subset of weights to update in each server-to-edge communication round, while achieving a similar performance compared to full updating. Our method is established through analytically upper-bounding the loss difference between partial updating and full updating, and only updates the weights which make the largest contributions to the upper bound. Extensive experimental results demonstrate the efficacy of our partial updating methodology which achieves a high inference accuracy while updating a rather small number of weights.

preprint2022arXiv

Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window. However, these hand-crafted window partition mechanisms are data-agnostic and ignore their input content, so it is likely that one query maybe attends to irrelevant keys/values. To address this issue, we propose a Dynamic Group Attention (DG-Attention), which dynamically divides all queries into multiple groups and selects the most relevant keys/values for each group. Our DG-Attention can flexibly model more relevant dependencies without any spatial constraint that is used in hand-crafted window based attention. Built on the DG-Attention, we develop a general vision transformer backbone named Dynamic Group Transformer (DGT). Extensive experiments show that our models can outperform the state-of-the-art methods on multiple common vision tasks, including image classification, semantic segmentation, object detection, and instance segmentation.

preprint2022arXiv

EREBA: Black-box Energy Testing of Adaptive Neural Networks

Recently, various Deep Neural Network (DNN) models have been proposed for environments like embedded systems with stringent energy constraints. The fundamental problem of determining the robustness of a DNN with respect to its energy consumption (energy robustness) is relatively unexplored compared to accuracy-based robustness. This work investigates the energy robustness of Adaptive Neural Networks (AdNNs), a type of energy-saving DNNs proposed for many energy-sensitive domains and have recently gained traction. We propose EREBA, the first black-box testing method for determining the energy robustness of an AdNN. EREBA explores and infers the relationship between inputs and the energy consumption of AdNNs to generate energy surging samples. Extensive implementation and evaluation using three state-of-the-art AdNNs demonstrate that test inputs generated by EREBA could degrade the performance of the system substantially. The test inputs generated by EREBA can increase the energy consumption of AdNNs by 2,000% compared to the original inputs. Our results also show that test inputs generated via EREBA are valuable in detecting energy surging inputs.

preprint2022arXiv

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Various approaches have been proposed for out-of-distribution (OOD) detection by augmenting models, input examples, training sets, and optimization objectives. Deviating from existing work, we have a simple hypothesis that standard off-the-shelf models may already contain sufficient information about the training set distribution which can be leveraged for reliable OOD detection. Our empirical study on validating this hypothesis, which measures the model activation's mean for OOD and in-distribution (ID) mini-batches, surprisingly finds that activation means of OOD mini-batches consistently deviate more from those of the training data. In addition, training data's activation means can be computed offline efficiently or retrieved from batch normalization layers as a 'free lunch'. Based upon this observation, we propose a novel metric called Neural Mean Discrepancy (NMD), which compares neural means of the input examples and training data. Leveraging the simplicity of NMD, we propose an efficient OOD detector that computes neural means by a standard forward pass followed by a lightweight classifier. Extensive experiments show that NMD outperforms state-of-the-art OOD approaches across multiple datasets and model architectures in terms of both detection accuracy and computational cost.

preprint2022arXiv

NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models

Neural image caption generation (NICG) models have received massive attention from the research community due to their excellent performance in visual understanding. Existing work focuses on improving NICG model accuracy while efficiency is less explored. However, many real-world applications require real-time feedback, which highly relies on the efficiency of NICG models. Recent research observed that the efficiency of NICG models could vary for different inputs. This observation brings in a new attack surface of NICG models, i.e., An adversary might be able to slightly change inputs to cause the NICG models to consume more computational resources. To further understand such efficiency-oriented threats, we propose a new attack approach, NICGSlowDown, to evaluate the efficiency robustness of NICG models. Our experimental results show that NICGSlowDown can generate images with human-unnoticeable perturbations that will increase the NICG model latency up to 483.86%. We hope this research could raise the community's concern about the efficiency robustness of NICG models.

preprint2022arXiv

Resonance induced by higher-order coupling diversity

The studies of collective oscillations induced by higher-order interactions point out the necessity of group effect in coupling modelization. As yet the related advances are mainly concentrated on nonlinear coupling patterns and cannot be straightforwardly extended to the linear ones. In present work, we introduce the standard deviation of dynamic behavior for the interacting group to complement the higher-order effect that beyond pairwise in diffusive coupling. By doing so, the higher-order effect can be flexibly extended to the linearly coupled system. We leverage this modelization to embrace the influence of heterogeneous higher-order coupling, including promoting and inhibiting effects, on the signal response for two conventional models, the globally coupled overdamped bistable oscillators and excitable FitzHugh-Nagumo neurons. Particularly, we numerically and analytically reveal that the optimal signal response can be obtained by an intermediate degree of higher-order coupling diversity for both systems. This resonant signal response stems from the competition between dispersion and aggregation induced by heterogeneous higher-order and positive pairwise couplings, respectively. Our results contribute to a better understanding of the signal propagation in linearly coupled systems.

preprint2022arXiv

Shear Measurement with Poorly Resolved Images

Weak lensing studies typically require excellent seeing conditions for the purpose of maximizing the number density of well-resolved galaxy images. It is interesting to ask to what extent the seeing size limits the usefulness of the astronomical images in weak lensing. In this work, we study this issue with the data of the DECam Legacy Survey (DECaLS), which is a part of the target selection program for the Dark Energy Spectroscopic Instrument (DESI). Using the Fourier Quad shear measurement pipeline, we demonstrate that images with relatively poor seeing conditions (around 1.5 arcsec) can still yield accurate shear estimators. We do not find any correlation between systematic shear error and the image resolution.

preprint2022arXiv

Xronos: Predictable Coordination for Safety-Critical Distributed Embedded Systems

Asynchronous frameworks for distributed embedded systems, like ROS and MQTT, are increasingly used in safety-critical applications such as autonomous driving, where the cost of unintended behavior is high. The coordination mechanism between the components in these frameworks, however, gives rise to nondeterminism, where factors such as communication timing can lead to arbitrary ordering in the handling of messages. In this paper, we demonstrate the significance of this problem in an open-source full-stack autonomous driving software, Autoware.Auto 1.0, which relies on ROS 2. We give an alternative: Xronos, an open-source framework for distributed embedded systems that has a novel coordination strategy with predictable properties under clearly stated assumptions. If these assumptions are violated, Xronos provides for application-specific fault handlers to be invoked. We port Autoware.Auto to Xronos and show that it avoids the identified problems with manageable cost in end-to-end latency. Furthermore, we compare the maximum throughput of Xronos to ROS 2 and MQTT using microbenchmarks under different settings, including on three different hardware configurations, and find that it can match or exceed those frameworks in terms of throughput.

preprint2021arXiv

Invariant in variants

The coronavirus Covid-19 mutates quickly in the pandemic, leaves people struggling to verify and improve the effectiveness of the vaccine based on biochemistry. Is there any physical invariant in the variants of such kind of pathogen that could be taken advantage to ease the tensions? To this point, extensive numerical experiments based on continuity mechanics were carried out to discover the vibration modes and the range of natural frequency of coronavirus Covid-19. Such invariant could help us in developing some flexible technique to deactivate the coronavirus, like as resonantly breaking the viral spike by ultrasound wave. The fundamental mechanisms governing such process are demonstrated via solving the coupled equations of acoustics and dynamics and thereafter the technique strategies proposed to efficiently realize the concept.

preprint2021arXiv

Partially Diffusive Helium-Silica Compound in the Deep Interiors of Giant Planets

Helium is the second most abundant element in the universe, and together with silica, they are major components of giant planets. Exploring the reactivity and state of helium and silica under high pressure is of fundamental importance for developing and understanding of the evolution and internal structure of giant planets. Here, using first-principles calculations and crystal structure predictions, we identify four stable phases of a helium-silica compound with seven/eight-coordinated silicon atoms at pressure range of 600-4000 GPa, corresponding to the interior condition of the outer planets in the solar system. The density of HeSiO2 agrees with current structure models of the planets. This helium-silica compound exhibits a superionic-like helium diffusive state at the high pressure and high temperature conditions along the isentropes of Saturn, a metallic fluid state in Jupiter, and a solid state in the deep interiors of Uranus and Neptune. The reaction of helium and silica may lead to the erosion of the rocky core of giant planets and form a diluted core region. These results highlight the reactivity of helium under high pressure to form new compounds, and also provides evidence to help build more sophisticated interior models of giant planets.

preprint2021arXiv

PredCoin: Defense against Query-based Hard-label Attack

Many adversarial attacks and defenses have recently been proposed for Deep Neural Networks (DNNs). While most of them are in the white-box setting, which is impractical, a new class of query-based hard-label (QBHL) black-box attacks pose a significant threat to real-world applications (e.g., Google Cloud, Tencent API). Till now, there has been no generalizable and practical approach proposed to defend against such attacks. This paper proposes and evaluates PredCoin, a practical and generalizable method for providing robustness against QBHL attacks. PredCoin poisons the gradient estimation step, an essential component of most QBHL attacks. PredCoin successfully identifies gradient estimation queries crafted by an attacker and introduces uncertainty to the output. Extensive experiments show that PredCoin successfully defends against four state-of-the-art QBHL attacks across various settings and tasks while preserving the target model's overall accuracy. PredCoin is also shown to be robust and effective against several defense-aware attacks, which may have full knowledge regarding the internal mechanisms of PredCoin.

preprint2021arXiv

Superionic silica-water and silica-hydrogen compounds under high pressure

Silica, water and hydrogen are known to be the major components of celestial bodies, and have significant influence on the formation and evolution of giant planets, such as Uranus and Neptune. Thus, it is of fundamental importance to investigate their states and possible reactions under the planetary conditions. Here, using advanced crystal structure searches and first-principles calculations in the Si-O-H system, we find that a silica-water compound (SiO2)2(H2O) and a silica-hydrogen compound SiO2H2 can exist under high pressures above 450 and 650 GPa, respectively. Further simulations reveal that, at high pressure and high temperature conditions corresponding to the interiors of Uranus and Neptune, these compounds exhibit superionic behavior, in which protons diffuse freely like liquid while the silicon and oxygen framework is fixed as solid. Therefore, these superionic silica-water and silica-hydrogen compounds could be regarded as important components of the deep mantle or core of giants, which also provides an alternative origin for their anomalous magnetic fields. These unexpected physical and chemical properties of the most common natural materials at high pressure offer key clues to understand some abstruse issues including demixing and erosion of the core in giant planets, and shed light on building reliable models for solar giants and exoplanets.

preprint2021arXiv

Turbulence-Resilient Coherent Free-Space Optical Communications using Automatic Power-Efficient Pilot-Assisted Optoelectronic Beam Mixing of Many Modes

Atmospheric turbulence generally limits free-space optical (FSO) communications, and this problem is severely exacerbated when implementing highly sensitive and spectrally efficient coherent detection. Specifically, turbulence induces power coupling from the transmitted Gaussian mode to higher-order Laguerre-Gaussian (LG) modes, resulting in a significant decrease of the power that mixes with a single-mode local oscillator (LO). Instead, we transmit a frequency-offset Gaussian pilot tone along with the data signal, such that both experience similar turbulence and modal power coupling. Subsequently, the photodetector (PD) optoelectronically mixes all corresponding pairs of the beams' modes. During mixing, a conjugate of the turbulence experienced by the pilot tone is automatically generated and compensates the turbulence experienced by the data, and nearly all orders of the same corresponding modes efficiently mix. We demonstrate a 12-Gbit/s 16-quadrature-amplitude-modulation (16-QAM) polarization-multiplexed (PolM) FSO link that exhibits resilience to emulated turbulence. Experimental results for turbulence D/r_0~5.5 show up to ~20 dB reduction in the mixing power loss over a conventional coherent receiver. Therefore, our approach automatically recovers nearly all the captured data power to enable high-performance coherent FSO systems.

preprint2020arXiv

CAVA: A Visual Analytics System for Exploratory Columnar Data Augmentation Using Knowledge Graphs

Most visual analytics systems assume that all foraging for data happens before the analytics process; once analysis begins, the set of data attributes considered is fixed. Such separation of data construction from analysis precludes iteration that can enable foraging informed by the needs that arise in-situ during the analysis. The separation of the foraging loop from the data analysis tasks can limit the pace and scope of analysis. In this paper, we present CAVA, a system that integrates data curation and data augmentation with the traditional data exploration and analysis tasks, enabling information foraging in-situ during analysis. Identifying attributes to add to the dataset is difficult because it requires human knowledge to determine which available attributes will be helpful for the ensuing analytical tasks. CAVA crawls knowledge graphs to provide users with a a broad set of attributes drawn from external data to choose from. Users can then specify complex operations on knowledge graphs to construct additional attributes. CAVA shows how visual analytics can help users forage for attributes by letting users visually explore the set of available data, and by serving as an interface for query construction. It also provides visualizations of the knowledge graph itself to help users understand complex joins such as multi-hop aggregations. We assess the ability of our system to enable users to perform complex data combinations without programming in a user study over two datasets. We then demonstrate the generalizability of CAVA through two additional usage scenarios. The results of the evaluation confirm that CAVA is effective in helping the user perform data foraging that leads to improved analysis outcomes, and offer evidence in support of integrating data augmentation as a part of the visual analytics pipeline.

preprint2020arXiv

Co-Optimizing Performance and Memory FootprintVia Integrated CPU/GPU Memory Management, anImplementation on Autonomous Driving Platform

Cutting-edge embedded system applications, such as self-driving cars and unmanned drone software, are reliant on integrated CPU/GPU platforms for their DNNs-driven workload, such as perception and other highly parallel components. In this work, we set out to explore the hidden performance implication of GPU memory management methods of integrated CPU/GPU architecture. Through a series of experiments on micro-benchmarks and real-world workloads, we find that the performance under different memory management methods may vary according to application characteristics. Based on this observation, we develop a performance model that can predict system overhead for each memory management method based on application characteristics. Guided by the performance model, we further propose a runtime scheduler. By conducting per-task memory management policy switching and kernel overlapping, the scheduler can significantly relieve the system memory pressure and reduce the multitasking co-run response time. We have implemented and extensively evaluated our system prototype on the NVIDIA Jetson TX2, Drive PX2, and Xavier AGX platforms, using both Rodinia benchmark suite and two real-world case studies of drone software and autonomous driving software.

preprint2020arXiv

InGaAs/InP single-photon detectors with 60% detection efficiency at 1550 nm

InGaAs/InP single-photon detectors (SPDs) are widely used for near-infrared photon counting in practical applications. Photon detection efficiency (PDE) is one of the most important parameters for SPD characterization, and therefore increasing PDE consistently plays a central role in both industrial development and academic research. Here we present the implementation of high-frequency gating InGaAs/InP SPD with a PDE as high as 60% at 1550 nm. On one hand, we optimize the structure design and device fabrication of InGaAs/InP single-photon avalanche diode with an additional dielectric-metal reflection layer to relatively increase the absorption efficiency of incident photons by ~ 20%. On the other hand, we develop a monolithic readout circuit of weak avalanche extraction to minimize the parasitic capacitance for the suppression of the afterpulsing effect. With 1.25 GHz sine wave gating and optimized gate amplitude and operation temperature, the SPD is characterized to reach a PDE of 60% with a dark count rate (DCR) of 340 kcps. For practical use, given 3 kcps DCR as a reference the PDE reaches ~ 40% PDE with an afterpulse probability of 5.5%, which can significantly improve the performance for the near-infrared SPD based applications.

preprint2020arXiv

LINTS^RT: A Learning-driven Testbed for Intelligent Scheduling in Embedded Systems

Due to the increasing complexity seen in both workloads and hardware resources in state-of-the-art embedded systems, developing efficient real-time schedulers and the corresponding schedulability tests becomes rather challenging. Although close to optimal schedulability performance can be achieved for supporting simple system models in practice, adding any small complexity element into the problem context such as non-preemption or resource heterogeneity would cause significant pessimism, which may not be eliminated by any existing scheduling technique. In this paper, we present LINTS^RT, a learning-based testbed for intelligent real-time scheduling, which has the potential to handle various complexities seen in practice. The design of LINTS^RT is fundamentally motivated by AlphaGo Zero for playing the board game Go, and specifically addresses several critical challenges due to the real-time scheduling context. We first present a clean design of LINTS^RT for supporting the basic case: scheduling sporadic workloads on a homogeneous multiprocessor, and then demonstrate how to easily extend the framework to handle further complexities such as non-preemption and resource heterogeneity. Both application and OS-level implementation and evaluation demonstrate that LINTS^RT is able to achieve significantly higher runtime schedulability under different settings compared to perhaps the most commonly applied schedulers, global EDF, and RM. To our knowledge, this work is the first attempt to design and implement an extensible learning-based testbed for autonomously making real-time scheduling decisions.

preprint2020arXiv

Performance of real-time adaptive optics compensation in a turbulent channel with high-dimensional spatial-mode encoding

The orbital angular momentum (OAM) of photons is a promising degree of freedom for high-dimensional quantum key distribution (QKD). However, effectively mitigating the adverse effects of atmospheric turbulence is a persistent challenge in OAM QKD systems operating over free-space communication channels. In contrast to previous works focusing on correcting static simulated turbulence, we investigate the performance of OAM QKD in real atmospheric turbulence with real-time adaptive optics (AO) correction. We show that, even our AO system provides a limited correction, it is possible to mitigate the errors induced by weak turbulence and establish a secure channel. The crosstalk induced by turbulence and the performance of AO systems is investigated in two configurations: a lab-scale link with controllable turbulence, and a 340 m long cross-campus link with dynamic atmospheric turbulence. Our experimental results suggest that an advanced AO system with fine beam tracking, reliable beam stabilization, precise wavefront sensing, and accurate wavefront correction is necessary to adequately correct turbulence-induced error. We also propose and demonstrate different solutions to improve the performance of OAM QKD with turbulence, which could enable the possibility of OAM encoding in strong turbulence.

preprint2020arXiv

PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural Networks

The black-box nature of deep neural networks (DNNs) facilitates attackers to manipulate the behavior of DNN through data poisoning. Being able to detect and mitigate poisoning attacks, typically categorized into backdoor and adversarial poisoning (AP), is critical in enabling safe adoption of DNNs in many application domains. Although recent works demonstrate encouraging results on detection of certain backdoor attacks, they exhibit inherent limitations which may significantly constrain the applicability. Indeed, no technique exists for detecting AP attacks, which represents a harder challenge given that such attacks exhibit no common and explicit rules while backdoor attacks do (i.e., embedding backdoor triggers into poisoned data). We believe the key to detect and mitigate AP attacks is the capability of observing and leveraging essential poisoning-induced properties within an infected DNN model. In this paper, we present PoisHygiene, the first effective and robust detection and mitigation framework against AP attacks. PoisHygiene is fundamentally motivated by Dr. Ernest Rutherford's story (i.e., the 1908 Nobel Prize winner), on observing the structure of atom through random electron sampling.