activity
20242026
collaborators

11 papers

cs.AI2026

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…

cs.CR2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.CV2026

Dynamic Token Reweighting for Robust Vision-Language Models

Tanqiu Jiang, Jiacheng Liang, Rongyi Zhu +3

Large vision-language models (VLMs) are highly vulnerable to multimodal jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we pr…

cs.AI2026

AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks

Tanqiu Jiang, Yuhui Wang, Jiacheng Liang +1

LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi…