Similar Items: ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming
- Autonomous Adversary: Red-Teaming in the age of LLM
- Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
- Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours
- TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
- SoK: Robustness in Large Language Models against Jailbreak Attacks
- FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption