Suicide Bot: New AI Attack Causes LLM to Provide Potential “Self-Harm” Instructions
No ratings
Presented at Blogosphere 2024 by
In this blog, we release two attacks against LLM systems, one of them successfully demonstrating how a widely used successful LLM can potentially instruct a girl on matters of "self-harm". We also make the claim that these attacks should be recognized as a new class of attacks, named Flowbreaking, affecting AI/ML-based system architecture for LLM applications and agents. These are logically similar in concept to race condition vulnerabilities in traditional software security.