2 citations · 2 across the 10 of their papers we have counts for
10 papers
RARE: Decoupling Representation Steering from Expert Routing in Mixture-of-Experts Language Models
Zhibo Zhang, Zhen Ouyang, Ling Shi +1
Representation engineering offers a lightweight means of controlling language-model behavior by modifying intermediate hidden states, but its direct application to Mixture-of-Exper…
TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
Zhibo Zhang, Zhen Ouyang, Ling Shi +1
Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities without model adaptation. Automa…
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
Yuxi Li, Zhibo Zhang, Kailong Wang +3
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or t…
RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMs
Zhibo Zhang, Yuxi Li, Zhen Ouyang +2
Mixture-of-Experts (MoE) LLMs rely on sparse, router-driven expert activation, yet how safety alignment interacts with routed expert specialization remains underexplored. A common…
When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion
Jiaqing Li, Zhibo Zhang, Shide Zhou +3
Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training costs. However, the security impl…
Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift
Shuai Yuan, Zhibo Zhang, Yuxi Li +2
The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform bas…