2 papers
cs.CR2026
OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
Longxiang Wang, Xiang Zheng, Xuhao Zhang +3
Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency. However, this creates side-channel vulnerabilities enabling prompt leakage attacks.…
cs.CR2025
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Guobin Shen, Dongcheng Zhao, Linghao Feng +8
Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit ha…