BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Ahmad-Reza Sadeghi

Ahmad-Reza Sadeghi appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Cryptography and SecurityMachine LearningSocial and Information Networkscs.CYHardware ArchitectureInformation RetrievalOperating SystemsSoftware Engineering

Catalog footprint

What is connected

14works
8topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

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

Published work

14 published item(s)

preprint2026arXiv

LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections

Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server, but the cut-layer interface introduces a key challenge: high-dimensional activations incur substantial communication overhead while exposing representations vulnerable to reconstruction attacks. Existing approaches typically address efficiency or privacy in isolation, relying on additional mechanisms such as sparsification, quantization, or noise injection. We propose LightSplit, which limits information exposure and reduces communication overhead by applying a lightweight fixed orthogonal random projection at the cut layer. Based on Shannon's information theory, this projection acts as an information bottleneck that restricts instance-specific information and suppresses exploitable per-sample signals. By transmitting low-dimensional projections instead of raw activations, the server operates on lifted representations without requiring architectural modifications, ensuring compatibility with existing SL architectures. By avoiding additional trainable components on the client, the method remains lightweight and suitable for edge devices while preserving end-to-end differentiability via exact gradient propagation. As the projection is non-invertible, part of the original representation is irreversibly discarded at the client, LightSplit reduces the information available for reconstruction and limits information exposure. We extensively evaluate LightSplit on state-of-the-art benchmarks in both IID and non-IID settings across varying projection dimensions and client scales. Our results show that the method retains more than 95% of the baseline accuracy at up to 32x reduction in transmitted dimensionality while maintaining stable training dynamics.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Fuzzilicon: A Post-Silicon Microcode-Guided x86 CPU Fuzzer

Modern CPUs are black boxes, proprietary, and increasingly characterized by sophisticated microarchitectural flaws that evade traditional analysis. While some of these critical vulnerabilities have been uncovered through cumbersome manual effort, building an automated and systematic vulnerability detection framework for real-world post-silicon processors remains a challenge. In this paper, we present Fuzzilicon, the first post-silicon fuzzing framework for real-world x86 CPUs that brings deep introspection into the microcode and microarchitectural layers. Fuzzilicon automates the discovery of vulnerabilities that were previously only detectable through extensive manual reverse engineering, and bridges the visibility gap by introducing microcode-level instrumentation. At the core of Fuzzilicon is a novel technique for extracting feedback directly from the processor's microarchitecture, enabled by reverse-engineering Intel's proprietary microcode update interface. We develop a minimally intrusive instrumentation method and integrate it with a hypervisor-based fuzzing harness to enable precise, feedback-guided input generation, without access to Register Transfer Level (RTL). Applied to Intel's Goldmont microarchitecture, Fuzzilicon introduces 5 significant findings, including two previously unknown microcode-level speculative-execution vulnerabilities. Besides, the Fuzzilicon framework automatically rediscover the $μ$Spectre class of vulnerabilities, which were detected manually in the previous work. Fuzzilicon reduces coverage collection overhead by up to 31$\times$ compared to baseline techniques and achieves 16.27% unique microcode coverage of hookable locations, the first empirical baseline of its kind. As a practical, coverage-guided, and scalable approach to post-silicon fuzzing, Fuzzilicon establishes a new foundation to automate the discovery of complex CPU vulnerabilities.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Follow Us and Become Famous! Insights and Guidelines From Instagram Engagement Mechanisms

With 1.3 billion users, Instagram (IG) has also become a business tool. IG influencer marketing, expected to generate $33.25 billion in 2022, encourages companies and influencers to create trending content. Various methods have been proposed for predicting a post's popularity, i.e., how much engagement (e.g., Likes) it will generate. However, these methods are limited: first, they focus on forecasting the likes, ignoring the number of comments, which became crucial in 2021. Secondly, studies often use biased or limited data. Third, researchers focused on Deep Learning models to increase predictive performance, which are difficult to interpret. As a result, end-users can only estimate engagement after a post is created, which is inefficient and expensive. A better approach is to generate a post based on what people and IG like, e.g., by following guidelines. In this work, we uncover part of the underlying mechanisms driving IG engagement. To achieve this goal, we rely on statistical analysis and interpretable models rather than Deep Learning (black-box) approaches. We conduct extensive experiments using a worldwide dataset of 10 million posts created by 34K global influencers in nine different categories. With our simple yet powerful algorithms, we can predict engagement up to 94% of F1-Score, making us comparable and even superior to Deep Learning-based method. Furthermore, we propose a novel unsupervised algorithm for finding highly engaging topics on IG. Thanks to our interpretable approaches, we conclude by outlining guidelines for creating successful posts.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been introduced. These attacks inject a backdoor into the resulting model that allows adversary-controlled inputs to be misclassified. Existing countermeasures against backdoor attacks are inefficient and often merely aim to exclude deviating models from the aggregation. However, this approach also removes benign models of clients with deviating data distributions, causing the aggregated model to perform poorly for such clients. To address this problem, we propose DeepSight, a novel model filtering approach for mitigating backdoor attacks. It is based on three novel techniques that allow to characterize the distribution of data used to train model updates and seek to measure fine-grained differences in the internal structure and outputs of NNs. Using these techniques, DeepSight can identify suspicious model updates. We also develop a scheme that can accurately cluster model updates. Combining the results of both components, DeepSight is able to identify and eliminate model clusters containing poisoned models with high attack impact. We also show that the backdoor contributions of possibly undetected poisoned models can be effectively mitigated with existing weight clipping-based defenses. We evaluate the performance and effectiveness of DeepSight and show that it can mitigate state-of-the-art backdoor attacks with a negligible impact on the model's performance on benign data.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

TheHuzz: Instruction Fuzzing of Processors Using Golden-Reference Models for Finding Software-Exploitable Vulnerabilities

The increasing complexity of modern processors poses many challenges to existing hardware verification tools and methodologies for detecting security-critical bugs. Recent attacks on processors have shown the fatal consequences of uncovering and exploiting hardware vulnerabilities. Fuzzing has emerged as a promising technique for detecting software vulnerabilities. Recently, a few hardware fuzzing techniques have been proposed. However, they suffer from several limitations, including non-applicability to commonly used Hardware Description Languages (HDLs) like Verilog and VHDL, the need for significant human intervention, and inability to capture many intrinsic hardware behaviors, such as signal transitions and floating wires. In this paper, we present the design and implementation of a novel hardware fuzzer, TheHuzz, that overcomes the aforementioned limitations and significantly improves the state of the art. We analyze the intrinsic behaviors of hardware designs in HDLs and then measure the coverage metrics that model such behaviors. TheHuzz generates assembly-level instructions to increase the desired coverage values, thereby finding many hardware bugs that are exploitable from software. We evaluate TheHuzz on four popular open-source processors and achieve 1.98x and 3.33x the speed compared to the industry-standard random regression approach and the state-of-the-art hardware fuzzer, DiffuzRTL, respectively. Using TheHuzz, we detected 11 bugs in these processors, including 8 new vulnerabilities, and we demonstrate exploits using the detected bugs. We also show that TheHuzz overcomes the limitations of formal verification tools from the semiconductor industry by comparing its findings to those discovered by the Cadence JasperGold tool.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Trusted Container Extensions for Container-based Confidential Computing

Cloud computing has emerged as a corner stone of today's computing landscape. More and more customers who outsource their infrastructure benefit from the manageability, scalability and cost saving that come with cloud computing. Those benefits get amplified by the trend towards microservices. Instead of renting and maintaining full VMs, customers increasingly leverage container technologies, which come with a much more lightweight resource footprint while also removing the need to emulate complete systems and their devices. However, privacy concerns hamper many customers from moving to the cloud and leveraging its benefits. Furthermore, regulatory requirements prevent the adaption of cloud computing in many industries, such as health care or finance. Standard software isolation mechanisms have been proven to be insufficient if the host system is not fully trusted, e.g., when the cloud infrastructure gets compromised by malicious third-party actors. Consequently, confidential computing is gaining increasing relevance in the cloud computing field. We present Trusted Container Extensions (TCX), a novel container security architecture, which combines the manageability and agility of standard containers with the strong protection guarantees of hardware-enforced Trusted Execution Environments (TEEs) to enable confidential computing for container workloads. TCX provides significant performance advantages compared to existing approaches while protecting container workloads and the data processed by them. Our implementation, based on AMD Secure Encrypted Virtualization (SEV), ensures integrity and confidentiality of data and services during deployment, and allows secure interaction between protected containers as well as to external entities. Our evaluation shows that our implementation induces a low performance overhead of 5.77% on the standard SPEC2017 benchmark suite.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

V'CER: Efficient Certificate Validation in Constrained Networks

We address the challenging problem of efficient trust establishment in constrained networks, i.e., networks that are composed of a large and dynamic set of (possibly heterogeneous) devices with limited bandwidth, connectivity, storage, and computational capabilities. Constrained networks are an integral part of many emerging application domains, from IoT meshes to satellite networks. A particularly difficult challenge is how to enforce timely revocation of compromised or faulty devices. Unfortunately, current solutions and techniques cannot cope with idiosyncrasies of constrained networks, since they mandate frequent real-time communication with centralized entities, storage and maintenance of large amounts of revocation information, and incur considerable bandwidth overhead. To address the shortcomings of existing solutions, we design V'CER, a secure and efficient scheme for certificate validation that augments and benefits a PKI for constrained networks. V'CER utilizes unique features of Sparse Merkle Trees (SMTs) to perform lightweight revocation checks, while enabling collaborative operations among devices to keep them up-to-date when connectivity to external authorities is limited. V'CER can complement any PKI scheme to increase its flexibility and applicability, while ensuring fast dissemination of validation information independent of the network routing or topology. V'CER requires under 3KB storage per node covering 106 certificates. We developed and deployed a prototype of V'CER on an in-orbit satellite and our large-scale simulations demonstrate that V'CER decreases the number of requests for updates from external authorities by over 93%, when nodes are intermittently connected.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Offline Model Guard: Secure and Private ML on Mobile Devices

Performing machine learning tasks in mobile applications yields a challenging conflict of interest: highly sensitive client information (e.g., speech data) should remain private while also the intellectual property of service providers (e.g., model parameters) must be protected. Cryptographic techniques offer secure solutions for this, but have an unacceptable overhead and moreover require frequent network interaction. In this work, we design a practically efficient hardware-based solution. Specifically, we build Offline Model Guard (OMG) to enable privacy-preserving machine learning on the predominant mobile computing platform ARM - even in offline scenarios. By leveraging a trusted execution environment for strict hardware-enforced isolation from other system components, OMG guarantees privacy of client data, secrecy of provided models, and integrity of processing algorithms. Our prototype implementation on an ARM HiKey 960 development board performs privacy-preserving keyword recognition using TensorFlow Lite for Microcontrollers in real time.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Peek-a-Boo: I see your smart home activities, even encrypted!

A myriad of IoT devices such as bulbs, switches, speakers in a smart home environment allow users to easily control the physical world around them and facilitate their living styles through the sensors already embedded in these devices. Sensor data contains a lot of sensitive information about the user and devices. However, an attacker inside or near a smart home environment can potentially exploit the innate wireless medium used by these devices to exfiltrate sensitive information from the encrypted payload (i.e., sensor data) about the users and their activities, invading user privacy. With this in mind,in this work, we introduce a novel multi-stage privacy attack against user privacy in a smart environment. It is realized utilizing state-of-the-art machine-learning approaches for detecting and identifying the types of IoT devices, their states, and ongoing user activities in a cascading style by only passively sniffing the network traffic from smart home devices and sensors. The attack effectively works on both encrypted and unencrypted communications. We evaluate the efficiency of the attack with real measurements from an extensive set of popular off-the-shelf smart home IoT devices utilizing a set of diverse network protocols like WiFi, ZigBee, and BLE. Our results show that an adversary passively sniffing the traffic can achieve very high accuracy (above 90%) in identifying the state and actions of targeted smart home devices and their users. To protect against this privacy leakage, we also propose a countermeasure based on generating spoofed traffic to hide the device states and demonstrate that it provides better protection than existing solutions.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

C-FLAT: Control-FLow ATtestation for Embedded Systems Software

Remote attestation is a crucial security service particularly relevant to increasingly popular IoT (and other embedded) devices. It allows a trusted party (verifier) to learn the state of a remote, and potentially malware-infected, device (prover). Most existing approaches are static in nature and only check whether benign software is initially loaded on the prover. However, they are vulnerable to run-time attacks that hijack the application's control or data flow, e.g., via return-oriented programming or data-oriented exploits. As a concrete step towards more comprehensive run-time remote attestation, we present the design and implementation of Control- FLow ATtestation (C-FLAT) that enables remote attestation of an application's control-flow path, without requiring the source code. We describe a full prototype implementation of C-FLAT on Raspberry Pi using its ARM TrustZone hardware security extensions. We evaluate C-FLAT's performance using a real-world embedded (cyber-physical) application, and demonstrate its efficacy against control-flow hijacking attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

OmniShare: Securely Accessing Encrypted Cloud Storage from Multiple Authorized Devices

Cloud storage services like Dropbox and Google Drive are widely used by individuals and businesses. Two attractive features of these services are 1) the automatic synchronization of files between multiple client devices and 2) the possibility to share files with other users. However, privacy of cloud data is a growing concern for both individuals and businesses. Encrypting data on the client-side before uploading it is an effective privacy safeguard, but it requires all client devices to have the decryption key. Current solutions derive these keys solely from user-chosen passwords, which have low entropy and are easily guessed. We present OmniShare, the first scheme to allow client-side encryption with high-entropy keys whilst providing an intuitive key distribution mechanism to enable access from multiple client devices. Instead of passwords, we use low bandwidth uni-directional out-of-band (OOB) channels, such as QR codes, to authenticate new devices. To complement these OOB channels, the cloud storage itself is used as a communication channel between devices in our protocols. We rely on a directory-based key hierarchy with individual file keys to limit the consequences of key compromise and allow efficient sharing of files without requiring re-encryption. OmniShare is open source software and currently available for Android and Windows with other platforms in development. We describe the design and implementation of OmniShare, and explain how we evaluated its security using formal methods, its performance via real-world benchmarks, and its usability through a cognitive walkthrough.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

SandBlaster: Reversing the Apple Sandbox

In order to limit the damage of malware on Mac OS X and iOS, Apple uses sandboxing, a kernel-level security layer that provides tight constraints for system calls. Particularly used for Apple iOS, sandboxing prevents apps from executing potentially dangerous actions, by defining rules in a sandbox profile. Investigating Apple's built-in sandbox profiles is difficult as they are compiled and stored in binary format. We present SandBlaster, a software bundle that is able to reverse/decompile Apple binary sandbox profiles to their original human readable SBPL (SandBox Profile Language) format. We use SandBlaster to reverse all built-in Apple iOS binary sandbox profiles for iOS 7, 8 and 9. Our tool is, to the best of our knowledge, the first to provide a full reversing of the Apple sandbox, shedding light into the inner workings of Apple sandbox profiles and providing essential support for security researchers and professionals interested in Apple security mechanisms.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

How Far Removed Are You? Scalable Privacy-Preserving Estimation of Social Path Length with Social PaL

Social relationships are a natural basis on which humans make trust decisions. Online Social Networks (OSNs) are increasingly often used to let users base trust decisions on the existence and the strength of social relationships. While most OSNs allow users to discover the length of the social path to other users, they do so in a centralized way, thus requiring them to rely on the service provider and reveal their interest in each other. This paper presents Social PaL, a system supporting the privacy-preserving discovery of arbitrary-length social paths between any two social network users. We overcome the bootstrapping problem encountered in all related prior work, demonstrating that Social PaL allows its users to find all paths of length two and to discover a significant fraction of longer paths, even when only a small fraction of OSN users is in the Social PaL system - e.g., discovering 70% of all paths with only 40% of the users. We implement Social PaL using a scalable server-side architecture and a modular Android client library, allowing developers to seamlessly integrate it into their apps.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

ConXsense - Automated Context Classification for Context-Aware Access Control

We present ConXsense, the first framework for context-aware access control on mobile devices based on context classification. Previous context-aware access control systems often require users to laboriously specify detailed policies or they rely on pre-defined policies not adequately reflecting the true preferences of users. We present the design and implementation of a context-aware framework that uses a probabilistic approach to overcome these deficiencies. The framework utilizes context sensing and machine learning to automatically classify contexts according to their security and privacy-related properties. We apply the framework to two important smartphone-related use cases: protection against device misuse using a dynamic device lock and protection against sensory malware. We ground our analysis on a sociological survey examining the perceptions and concerns of users related to contextual smartphone security and analyze the effectiveness of our approach with real-world context data. We also demonstrate the integration of our framework with the FlaskDroid architecture for fine-grained access control enforcement on the Android platform.

0 citations0 reviewsNo code linkedOpen access