YU LI

SafeMVDrive: Multi-view Safety-Critical Driving Video Generation in the Real World Domain

BEVCA: Effective and Transferable Camouflage Attack against Multi-View 3D Perception in Autonomous Driving

Jailbreak LEGO: A Compositional Benchmark for Red-Teaming LLMs

SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs

Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs

Function-to-Style Guidance of LLMs for Code Translation

Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization

An Adaptive Defense Against Adversarial Patch Attacks For Vision Transformers