13 papers
LaCache: Robust Semantic Caching for LLM Serving
Jiacheng Liang, Yuhui Wang, Tanqiu Jiang +1
Semantic caching, which reuses responses to semantically similar requests via their embeddings, has seen growing adoption in LLM serving, offering faster responses and reduced cost…
MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
Yuhui Wang, Tanqiu Jiang, Jiacheng Liang +2
As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-e…
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
Jiacheng Liang, Yao Ma, Tharindu Kumarage +5
Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an imperfect Reward Model (RM) ca…
AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models
Jiacheng Liang, Tanqiu Jiang, Yuhui Wang +3
This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in large reasoning models (LRMs). At its core, AutoRAN pioneers an execution…
RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
Jiacheng Liang, Yuhui Wang, Tanqiu Jiang +1
Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable degenerate optimization behaviors…
Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models
Yuhui Wang, Changjiang Li, Guangke Chen +2
Large reasoning models (LRMs) exhibit unprecedented capabilities in solving complex problems through Chain-of-Thought (CoT) reasoning. However, recent studies reveal that their fin…