5 papers
Safety in Self-Evolving Agents: A Survey
Jiahao Chen, Zhou Feng, Oubo Ma +28
Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from new interactions. In open-end…
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
Mengyao Du, Han Fang, Haokai Ma +4
Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious i…
TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
Mengyao Du, Han Fang, Haokai Ma +4
Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit…
Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier
Mengyao Du, Gang Yang, Han Fang +2
The widespread adoption of natural language processing techniques has led to an unprecedented growth of text classifiers across the modern web. Yet many of these models circulate w…
The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness
Mengyao Du, Miao Zhang, Yuwen Pu +3
To tackle the scarcity and privacy issues associated with domain-specific datasets, the integration of federated learning in conjunction with fine-tuning has emerged as a practical…