Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
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…
cs.CR2026
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…
cs.CR2026
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…