#MultiTurnAttack
LLM safety isn't only about individual turns.

Each message can look clean. The whole sequence can still be the attack.

Threat model + defense framework for Symbolic Interaction Attacks on LLMs.

doi.org/10.5281/zeno...

#LLMSafety #AIRedTeaming #AIGovernance #MultiTurnAttack #ContextualSecurity
When Psychological Operations Meet Language Models: A Defense Framework for Symbolic Interaction Attacks on LLMs
Abstract Large language models (LLMs) are increasingly evaluated against prompt injection, jailbreaks, harmful content generation, and other turn-level security threats. Recent research has also demon...
doi.org
September 27, 2026 at 12:42 AM