Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Sign inBecome a Member
Home/Research Paper Library/Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

Applied adaptive-attack methodology to agent prompt-injection defences and broke all eight tested, extending the adversarial-ML lesson to LLM agents.

adaptive attacksagentsdefences

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.