Shun Kashiwa (UC San Diego), Michael Coblenz (UC San Diego), Deian Stefan (UC San Diego)
Work-in-progress: Assertive Trace
View More Papers
Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models
Linzhi Chen (ShanghaiTech University), Yang Sun (Independent Researcher), Hongru Wei (ShanghaiTech University), Yuqi Chen (ShanghaiTech University)
Read MoreNeuroStrike: Neuron-Level Attacks on Aligned LLMs
Lichao Wu (Technical University of Darmstadt), Sasha Behrouzi (Technical University of Darmstadt), Mohamadreza Rostami (Technical University of Darmstadt), Maximilian Thang (Technical University of Darmstadt), Stjepan Picek (University of Zagreb & Radboud University), Ahmad-Reza Sadeghi (Technical University of Darmstadt)
Read More