1 citations · 2 across the 13 of their papers we have counts for
15 papers
LaCache: Robust Semantic Caching for LLM Serving
Jiacheng Liang, Yuhui Wang, Tanqiu Jiang +1
Semantic caching, reusing responses to answer semantically similar queries, has seen growing adoption in LLM serving, offering faster responses and reduced costs. Yet existing sche…
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…
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…
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…
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…
Self-Improving Model Steering
Rongyi Zhu, Yuhui Wang, Tanqiu Jiang +2
Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering me…
Your Agent Can Defend Itself against Backdoor Attacks
Li Changjiang, Liang Jiacheng, Cao Bochuan +2
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. Thes…
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…
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…
GraphRAG under Fire
Jiacheng Liang, Yuhui Wang, Changjiang Li +4
GraphRAG advances retrieval-augmented generation (RAG) by structuring external knowledge as multi-scale knowledge graphs, enabling language models to integrate both broad context a…
CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models
Naen Xu, Changjiang Li, Tianyu Du +8
Text-to-image diffusion models have emerged as powerful tools for generating high-quality images from textual descriptions. However, their increasing popularity has raised signific…
Watermark under Fire: A Robustness Evaluation of LLM Watermarking
Jiacheng Liang, Zian Wang, Lauren Hong +2
Various watermarking methods (``watermarkers'') have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions re…
RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
Tanqiu Jiang, Zian Wang, Jiacheng Liang +3
Jailbreak attacks circumvent LLMs' built-in safeguards by concealing harmful queries within jailbreak prompts. While existing defenses primarily focus on mitigating the effects of…
Model Extraction Attacks Revisited
Jiacheng Liang, Ren Pang, Changjiang Li +1
Model extraction (ME) attacks represent one major threat to Machine-Learning-as-a-Service (MLaaS) platforms by ``stealing'' the functionality of confidential machine-learning model…