Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Paper
•
2401.05566
•
Published
•
27
Ai-hacking
-
-
Weak-to-Strong Jailbreaking on Large Language Models
Paper • 2401.17256 • Published • 16 -
How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts
Paper • 2402.13220 • Published • 14 -
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Paper • 2404.13208 • Published • 39 -
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
Paper • 2404.16873 • Published • 29 -
SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models
Paper • 2405.08317 • Published • 11 -
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
Paper • 2407.12784 • Published • 49