43 citations · 63 across the 10 of their papers we have counts for
10 papers
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…
Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection
Tian Dong, Yanjun Chen, Shoufeng Zhang +6
AI infra has become a shared execution layer for model training, deployment, and agent orchestration. Because many projects reimplement similar model-centric workflows, a vulnerabi…
Depth Gives a False Sense of Privacy: LLM Internal States Inversion
Tian Dong, Yan Meng, Shaofeng Li +3
Large Language Models (LLMs) are increasingly integrated into daily routines, yet they raise significant privacy and safety concerns. Recent research proposes collaborative inferen…
Model Inversion in Split Learning for Personalized LLMs: New Insights from Information Bottleneck Theory
Yunmeng Shu, Shaofeng Li, Tian Dong +2
Personalized Large Language Models (LLMs) have become increasingly prevalent, showcasing the impressive capabilities of models like GPT-4. This trend has also catalyzed extensive r…
The Philosopher's Stone: Trojaning Plugins of Large Language Models
Tian Dong, Minhui Xue, Guoxing Chen +5
Open-source Large Language Models (LLMs) have recently gained popularity because of their comparable performance to proprietary LLMs. To efficiently fulfill domain-specialized task…
Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations
Zirui Peng, Shaofeng Li, Guoxing Chen +3
In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction…
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,…
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…
Deep Learning Backdoors
Shaofeng Li, Shiqing Ma, Minhui Xue +1
Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign in…
Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
Shaofeng Li, Minhui Xue, Benjamin Zi Hao Zhao +2
Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific in…