13 papers
LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
Yaopeng Wang, Qingliang Wang, Zhibo Wang +5
Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing text-to-image diffusion models, enabling lightweight modules that are shared, reused, and commercializ…
RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
Bo Lv, Zhiheng Xu, KeDong Xiu +4
As Mixture-of-Experts (MoE) architectures are increasingly adopted for scaling Large Language Models (LLMs), safety auditing becomes necessary to verify whether these models produc…
LoopTrap: Termination Poisoning Attacks on LLM Agents
Huiyu Xu, Zhibo Wang, Wenhui Zhang +4
Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to determine when a task is complete.…
Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
Bo Wang, Jia Ni, Mengnan Zhao +2
The unauthorized use of personal data in model training has emerged as a growing privacy threat. Unlearnable examples (UEs) address this issue by embedding imperceptible perturbati…
QCFuse: Query-Centric Cache Fusion for Efficient RAG Inference
Jianxin Yan, Zeheng Qian, Wangze Ni +6
Cache fusion accelerates generation process of LLMs equipped with RAG through KV caching and selective token recomputation, thereby reducing computational costs and improving effic…
RerouteGuard: Understanding and Mitigating Adversarial Risks for LLM Routing
Wenhui Zhang, Huiyu Xu, Zhibo Wang +4
Recent advancements in multi-model AI systems have leveraged LLM routers to reduce computational cost while maintaining response quality by assigning queries to the most appropriat…