adversarial prompts

4 papers

• SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
• Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
• T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
• VERA: Variational Inference Framework for Jailbreaking Large Language Models