Zhiyuan Xu
zhiyuan16bristol
AI & ML interests
None yet
Recent Activity
authored a paper 3 days ago
NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation authored a paper 6 months ago
Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models authored a paper 6 months ago
RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMsOrganizations
None yet