Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM Agents
The explosive prompt is introduced, a conditional payload that stays dormant until an attacker-chosen trigger is met, in effect a training-free, inference-time backdoor planted in a single piece of retrieved content.
Justin Szczepaniak, Elad Feldman, Naum Viner et al.
· 0 citations