31 citations · 48 across the 11 of their papers we have counts for
13 papers
Evaluating and Improving Static Application Security Testing Tools for Rust
Huaien Zhang, Zhengjie Zhao, Yu Pei +4
Rust has become a popular systems programming language in recent years because of its strong guarantees on memory and concurrency safety. Many types of system software have been re…
Chaining Skills to Hijack LLM Agents
Tian Dong, Zixuan Ma, Haodong Zhao +3
LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowing information produced under o…
VulnGym: Benchmarking Coding Agents for Repository-Level Vulnerability Detection
Kexing Ji, Jiachen Liu, Enze Hu +7
Recent advances in LLM-based vulnerability detection have shown promising results, while coding agents further extend this capability from isolated code snippets to complete reposi…
Measuring Behavior Portability in Large Language Models
Tianjia Dong, Nadav Kunievsky, James A. Evans
Large language models are increasingly deployed as autonomous decision makers, yet the behavioral mapping they exhibit can vary substantially across decision environments that are…
DIPBox: A Multi-scale Testing Framework for Tracking Dataset Regeneration
Tian Dong, Yan Meng, Shaofeng Li +5
Training datasets have tremendous proprietary value and are vulnerable to unauthorized copying. Existing defenses mainly focus on tracking individual data points, but pay little at…
AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents
Yutao Luo, Haotian Zhu, Shuchao Pang +4
The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Ex…
Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs
Han Yang, Shaofeng Li, Tian Dong +3
Deep Neural Networks (DNNs), as valuable intellectual property, face unauthorized use. Existing protections, such as digital watermarking, are largely passive; they provide only po…
Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing
Tian Dong, Ziyuan Zhang, Han Qiu +3
Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing…
Privacy for Free: How does Dataset Condensation Help Privacy?
Tian Dong, Bo Zhao, Lingjuan Lyu
To prevent unintentional data leakage, research community has resorted to data generators that can produce differentially private data for model training. However, for the sake of…
An Interpretable Federated Learning-based Network Intrusion Detection Framework
Tian Dong, Song Li, Han Qiu +1
Learning-based Network Intrusion Detection Systems (NIDSs) are widely deployed for defending various cyberattacks. Existing learning-based NIDS mainly uses Neural Network (NN) as a…
Mate! Are You Really Aware? An Explainability-Guided Testing Framework for Robustness of Malware Detectors
Ruoxi Sun, Minhui Xue, Gareth Tyson +6
Numerous open-source and commercial malware detectors are available. However, their efficacy is threatened by new adversarial attacks, whereby malware attempts to evade detection,…
Fingerprinting Multi-exit Deep Neural Network Models via Inference Time
Tian Dong, Han Qiu, Tianwei Zhang +3
Transforming large deep neural network (DNN) models into the multi-exit architectures can overcome the overthinking issue and distribute a large DNN model on resource-constrained s…
Hidden Backdoors in Human-Centric Language Models
Shaofeng Li, Hui Liu, Tian Dong +4
Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only…