Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
Zekun Fei, Zihao Wang, Weijie Liu +4
Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduc…
cs.CR2025
Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
Jianing Geng, Biao Yi, Zekun Fei +4
Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness bu…
cs.CR2024
Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
Zekun Fei, Biao Yi, Jianing Geng +3
Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, particularly, the AP…