arXiv subjects

Chongzhou Fang

Publications and source records attributed to Chongzhou Fang.

14 recordsLinked to original sources

arXiv2026

Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents

Long-horizon security LLM agents must carry information and decisions across many dependent interactions, where later actions often depend on services, state, or access discovered much earlier. This makes final task success difficult to interpret: an agent may fail before it ever reaches the point where the capability of interest can be exercised. We present a diagnostic methodology that instruments security tasks with checkpoints, separates failures before and after capability exposure, and uses controlled interventions to test suspected upstream bottlenecks. We evaluate the methodology across four task families involving delayed reuse of discovered information, reuse of observed state, recovery from failed strategies, and decision making after uncertain outcomes. On observed state reuse, checkpoint analysis shows that many Gemini 2.5 Flash failures occur before the model observes the state it is later expected to reuse. In a pre-specified 92-seed study, targeted protocol-disambiguation guidance increases state observation from 65.5\% under a matched non-guidance control message to 95.4\%. Repeating the same design with Gemini 3.7 Flash produces the opposite effect, while state observation no longer reliably predicts task completion. These results show that the dominant source of failure can shift across model generations, motivating evaluation that diagnoses where and why long-horizon security agents fail rather than relying only on aggregate task success.

cs.CR↗

arXiv2026

Faults That Fortify: CNN Adversarial Robustness via GPU Undervolting

Convolutional Neural Networks (CNNs) face a dual challenge: vulnerability to adversarial attacks and prohibitive training cost. Adversarial training is effective but expensive, a burden that grows as learning shifts to the energy-constrained edge. This paper addresses both through GPU undervolting during training. Reducing supply voltage introduces stochastic perturbations that act as implicit regularization, improving robustness while lowering power. We characterize undervolting-induced faults at the bit level, then train LeNet, VGG-6, and MobileNetV3 on MNIST and CIFAR-10 under two training regimes, standard and adversarial, each at nominal and undervolted voltage, and evaluate all models against adversarial attacks. In both regimes, the undervolted model consistently achieves higher adversarial accuracy than its nominal-voltage counterpart, showing that hardware-induced faults strengthen even adversarial training. Because dynamic power scales quadratically with supply voltage, these robustness gains arrive with substantial energy savings. GPU undervolting is therefore a readily deployable hardware-level defense requiring no algorithmic change, and opens a promising direction in which robustness and energy efficiency move together.

cs.LG↗

arXiv2026

Kumo: A Security-Focused Serverless Cloud Simulator

Serverless computing abstracts infrastructure management but also obscures system-level behaviors that can introduce security risks. Prior work has shown that serverless platforms are vulnerable to attacks exploiting shared execution environments, including attacker--victim co-location and denial-of-service through resource contention, yet analyzing these risks on production platforms is difficult due to limited observability, high cost, and lack of experimental control, while existing simulators primarily focus on performance and cost rather than security. We present Kumo, a security-focused simulator for serverless platforms that enables controlled, reproducible analysis of security risks arising from scheduling and resource sharing decisions. Kumo models invocation arrivals, scheduler placement, container reuse, resource contention, and queuing within a discrete-event framework, explicitly representing attackers and victims as first-class entities and providing metrics such as co-location probability, time to first co-location, invocation drop rate, and tail latency. Through two case studies, we show that scheduler choice is a first-order factor for co-location attacks, inducing orders-of-magnitude differences under identical workloads, while Denial-of-Service behavior is largely governed by system-level factors such as service time, queuing policy, and cluster capacity once contention dominates. These results highlight the need to distinguish scheduler-driven isolation risks from broader resource exhaustion vulnerabilities and position Kumo as a flexible foundation for systematic, security-aware exploration of serverless platforms.

cs.CR↗

arXiv2025

Bit of a Close Talker: A Practical Guide to Serverless Cloud Co-Location Attacks

Serverless computing has revolutionized cloud computing by offering users an efficient, cost-effective way to develop and deploy applications without managing infrastructure details. However, serverless cloud users remain vulnerable to various types of attacks, including micro-architectural side-channel attacks. These attacks typically rely on the physical co-location of victim and attacker instances, and attackers need to exploit cloud schedulers to achieve co-location with victims. Therefore, it is crucial to study vulnerabilities in serverless cloud schedulers and assess the security of different serverless scheduling algorithms. This study addresses the gap in understanding and constructing co-location attacks in serverless clouds. We present a comprehensive methodology to uncover exploitable features in serverless scheduling algorithms and to devise strategies for constructing co-location attacks via normal user interfaces. In our experiments, we successfully reveal exploitable vulnerabilities and achieve instance co-location on prevalent open-source infrastructures and Microsoft Azure Functions. We also present a mitigation strategy, the Double-Dip scheduler, to defend against co-location attacks in serverless clouds. Our work highlights critical areas for security enhancements in current cloud schedulers, offering insights to fortify serverless computing environments against potential co-location attacks.

cs.CR↗

arXiv2025

FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models

Forget and Rewire (FaR) methodology has demonstrated strong resilience against Bit-Flip Attacks (BFAs) on Transformer-based models by obfuscating critical parameters through dynamic rewiring of linear layers. However, the application of FaR introduces non-negligible performance and memory overheads, primarily due to the runtime modification of activation pathways and the lack of hardware-level optimization. To overcome these limitations, we propose FaRAccel, a novel hardware accelerator architecture implemented on FPGA, specifically designed to offload and optimize FaR operations. FaRAccel integrates reconfigurable logic for dynamic activation rerouting, and lightweight storage of rewiring configurations, enabling low-latency inference with minimal energy overhead. We evaluate FaRAccel across a suite of Transformer models and demonstrate substantial reductions in FaR inference latency and improvement in energy efficiency, while maintaining the robustness gains of the original FaR methodology. To the best of our knowledge, this is the first hardware-accelerated defense against BFAs in Transformers, effectively bridging the gap between algorithmic resilience and efficient deployment on real-world AI platforms.

cs.CR↗

arXiv2025

Know Me by My Pulse: Toward Practical Continuous Authentication on Wearable Devices via Wrist-Worn PPG

Biometric authentication using physiological signals offers a promising path toward secure and user-friendly access control in wearable devices. While electrocardiogram (ECG) signals have shown high discriminability, their intrusive sensing requirements and discontinuous acquisition limit practicality. Photoplethysmography (PPG), on the other hand, enables continuous, non-intrusive authentication with seamless integration into wrist-worn wearable devices. However, most prior work relies on high-frequency PPG (e.g., 75 - 500 Hz) and complex deep models, which incur significant energy and computational overhead, impeding deployment in power-constrained real-world systems. In this paper, we present the first real-world implementation and evaluation of a continuous authentication system on a smartwatch, We-Be Band, using low-frequency (25 Hz) multi-channel PPG signals. Our method employs a Bi-LSTM with attention mechanism to extract identity-specific features from short (4 s) windows of 4-channel PPG. Through extensive evaluations on both public datasets (PTTPPG) and our We-Be Dataset (26 subjects), we demonstrate strong classification performance with an average test accuracy of 88.11%, macro F1-score of 0.88, False Acceptance Rate (FAR) of 0.48%, False Rejection Rate (FRR) of 11.77%, and Equal Error Rate (EER) of 2.76%. Our 25 Hz system reduces sensor power consumption by 53% compared to 512 Hz and 19% compared to 128 Hz setups without compromising performance. We find that sampling at 25 Hz preserves authentication accuracy, whereas performance drops sharply at 20 Hz while offering only trivial additional power savings, underscoring 25 Hz as the practical lower bound. Additionally, we find that models trained exclusively on resting data fail under motion, while activity-diverse training improves robustness across physiological states.

cs.CR↗

arXiv2024

APEX: Attention on Personality based Emotion ReXgnition Framework

Automated emotion recognition has applications in various fields, such as human-machine interaction, healthcare, security, education, and emotion-aware recommendation/feedback systems. Developing methods to analyze human emotions accurately is essential to enable such diverse applications. Multiple studies have been conducted to explore the possibility of using physiological signals and machine-learning techniques to evaluate human emotions. Furthermore, internal factors such as personality have been considered and involved in emotion recognition. However, integrating personality that is user specific within traditional machine-learning methods that use user-agnostic large data sets has become a critical problem. This study proposes the APEX: attention on personality-based emotion recognition framework, in which multiple weak classifiers are trained on physiological signals of each participant's data, and the classification results are reweighed based on the personality correlations between corresponding subjects and test subjects. Experiments have been conducted on the ASCERTAIN dataset, and the results show that the proposed framework outperforms existing studies.

eess.SY↗

arXiv2024

Advanced Energy-Efficient System for Precision Electrodermal Activity Monitoring in Stress Detection

This paper presents a novel Electrodermal Activity (EDA) signal acquisition system, designed to address the challenges of stress monitoring in contemporary society, where stress affects one in four individuals. Our system focuses on enhancing the accuracy and efficiency of EDA measurements, a reliable indicator of stress. Traditional EDA monitoring solutions often grapple with trade-offs between sensor placement, cost, and power consumption, leading to compromised data accuracy. Our innovative design incorporates an adaptive gain mechanism, catering to the broad dynamic range and high-resolution needs of EDA data analysis. The performance of our system was extensively tested through simulations and a custom Printed Circuit Board (PCB), achieving an error rate below 1\% and maintaining power consumption at a mere 700$μ$A under a 3.7V power supply. This research contributes significantly to the field of wearable health technology, offering a robust and efficient solution for long-term stress monitoring.

eess.SY↗

arXiv2024

Fuzzing BusyBox: Leveraging LLM and Crash Reuse for Embedded Bug Unearthing

BusyBox, an open-source software bundling over 300 essential Linux commands into a single executable, is ubiquitous in Linux-based embedded devices. Vulnerabilities in BusyBox can have far-reaching consequences, affecting a wide array of devices. This research, driven by the extensive use of BusyBox, delved into its analysis. The study revealed the prevalence of older BusyBox versions in real-world embedded products, prompting us to conduct fuzz testing on BusyBox. Fuzzing, a pivotal software testing method, aims to induce crashes that are subsequently scrutinized to uncover vulnerabilities. Within this study, we introduce two techniques to fortify software testing. The first technique enhances fuzzing by leveraging Large Language Models (LLM) to generate target-specific initial seeds. Our study showed a substantial increase in crashes when using LLM-generated initial seeds, highlighting the potential of LLM to efficiently tackle the typically labor-intensive task of generating target-specific initial seeds. The second technique involves repurposing previously acquired crash data from similar fuzzed targets before initiating fuzzing on a new target. This approach streamlines the time-consuming fuzz testing process by providing crash data directly to the new target before commencing fuzzing. We successfully identified crashes in the latest BusyBox target without conducting traditional fuzzing, emphasizing the effectiveness of LLM and crash reuse techniques in enhancing software testing and improving vulnerability detection in embedded systems. Additionally, manual triaging was performed to identify the nature of crashes in the latest BusyBox.

cs.SE↗

arXiv2024

Large Language Models for Code Analysis: Do LLMs Really Do Their Job?

Large language models (LLMs) have demonstrated significant potential in the realm of natural language understanding and programming code processing tasks. Their capacity to comprehend and generate human-like code has spurred research into harnessing LLMs for code analysis purposes. However, the existing body of literature falls short in delivering a systematic evaluation and assessment of LLMs' effectiveness in code analysis, particularly in the context of obfuscated code. This paper seeks to bridge this gap by offering a comprehensive evaluation of LLMs' capabilities in performing code analysis tasks. Additionally, it presents real-world case studies that employ LLMs for code analysis. Our findings indicate that LLMs can indeed serve as valuable tools for automating code analysis, albeit with certain limitations. Through meticulous exploration, this research contributes to a deeper understanding of the potential and constraints associated with utilizing LLMs in code analysis, paving the way for enhanced applications in this critical domain.

cs.SE↗

arXiv2023

Gotcha! I Know What You are Doing on the FPGA Cloud: Fingerprinting Co-Located Cloud FPGA Accelerators via Measuring Communication Links

In recent decades, due to the emerging requirements of computation acceleration, cloud FPGAs have become popular in public clouds. Major cloud service providers, e.g. AWS and Microsoft Azure have provided FPGA computing resources in their infrastructure and have enabled users to design and deploy their own accelerators on these FPGAs. Multi-tenancy FPGAs, where multiple users can share the same FPGA fabric with certain types of isolation to improve resource efficiency, have already been proved feasible. However, this also raises security concerns. Various types of side-channel attacks targeting multi-tenancy FPGAs have been proposed and validated. The awareness of security vulnerabilities in the cloud has motivated cloud providers to take action to enhance the security of their cloud environments. In FPGA security research papers, researchers always perform attacks under the assumption that attackers successfully co-locate with victims and are aware of the existence of victims on the same FPGA board. However, the way to reach this point, i.e., how attackers secretly obtain information regarding accelerators on the same fabric, is constantly ignored despite the fact that it is non-trivial and important for attackers. In this paper, we present a novel fingerprinting attack to gain the types of co-located FPGA accelerators. We utilize a seemingly non-malicious benchmark accelerator to sniff the communication link and collect performance traces of the FPGA-host communication link. By analyzing these traces, we are able to achieve high classification accuracy for fingerprinting co-located accelerators, which proves that attackers can use our method to perform cloud FPGA accelerator fingerprinting with a high success rate. As far as we know, this is the first paper targeting multi-tenant FPGA accelerator fingerprinting with the communication side-channel.

cs.CR↗

arXiv2023

Side Channel-Assisted Inference Leakage from Machine Learning-based ECG Classification

The Electrocardiogram (ECG) measures the electrical cardiac activity generated by the heart to detect abnormal heartbeat and heart attack. However, the irregular occurrence of the abnormalities demands continuous monitoring of heartbeats. Machine learning techniques are leveraged to automate the task to reduce labor work needed during monitoring. In recent years, many companies have launched products with ECG monitoring and irregular heartbeat alert. Among all classification algorithms, the time series-based algorithm dynamic time warping (DTW) is widely adopted to undertake the ECG classification task. Though progress has been achieved, the DTW-based ECG classification also brings a new attacking vector of leaking the patients' diagnosis results. This paper shows that the ECG input samples' labels can be stolen via a side-channel attack, Flush+Reload. In particular, we first identify the vulnerability of DTW for ECG classification, i.e., the correlation between warping path choice and prediction results. Then we implement an attack that leverages Flush+Reload to monitor the warping path selection with known ECG data and then build a predictor for constructing the relation between warping path selection and labels of input ECG samples. Based on experiments, we find that the Flush+Reload-based inference leakage can achieve an 84.0\% attacking success rate to identify the labels of the two samples in DTW.

cs.CR↗

arXiv2022

Predictive Modeling of Charge Levels for Battery Electric Vehicles using CNN EfficientNet and IGTD Algorithm

Convolutional Neural Networks (CNN) have been a good solution for understanding a vast image dataset. As the increased number of battery-equipped electric vehicles is flourishing globally, there has been much research on understanding which charge levels electric vehicle drivers would choose to charge their vehicles to get to their destination without any prevention. We implemented deep learning approaches to analyze the tabular datasets to understand their state of charge and which charge levels they would choose. In addition, we implemented the Image Generator for Tabular Dataset algorithm to utilize tabular datasets as image datasets to train convolutional neural networks. Also, we integrated other CNN architecture such as EfficientNet to prove that CNN is a great learner for reading information from images that were converted from the tabular dataset, and able to predict charge levels for battery-equipped electric vehicles. We also evaluated several optimization methods to enhance the learning rate of the models and examined further analysis on improving the model architecture.

cs.CV↗

arXiv2021

Repttack: Exploiting Cloud Schedulers to Guide Co-Location Attacks

Cloud computing paradigms have emerged as a major facility to store and process the massive data produced by various business units, public organizations, Internet-of-Things, and cyber-physical systems. To meet users' performance requirements while maximizing resource utilization to achieve cost-efficiency, cloud administrators leverage schedulers to orchestrate tasks to different physical nodes and allow applications from different users to share the same physical node. On the other hand, micro-architectural attacks can exploit the shared resources to compromise the confidentiality/integrity of a co-located victim application. Since co-location is an essential requirement for micro-architectural attacks, in this work, we investigate whether attackers can exploit the cloud schedulers to satisfy the co-location requirement. Our analysis shows that for cloud schedulers that allow users to submit application requirements, an attacker can carefully select the attacker's application requirements to influence the scheduler to co-locate it with a targeted victim application. We call such attack Replication Attack (Repttack). Our experimental results, in both a simulated cluster environment and a real cluster, show similar trends; a single attack instance can reach up to 50% co-location rate and with only 5 instances the co-location rate can reach up to 80%. Furthermore, we propose and evaluate a mitigation strategy that can help defend against Repttack. We believe that our results highlight the fact that schedulers in multi-user clusters need to be more carefully designed with security in mind, and the process of making scheduling decisions should involve as little user-defined information as possible.

cs.DC↗