Goal Hijacking Attack on Large Language Models via Pseudo-Conversation Injection

ArXi:2410.23678v2 Announce Type: replace Goal hijacking is a type of adversarial attack on Large Language Models (LLMs) where the objective is to manipulate the model into producing a specific, predetermined output, regardless of the user's original input. In goal hijacking, an attacker typically appends a carefully crafted malicious suffix to the user's prompt, which coerces the model into ignoring the user's original input and generating the target response. In this paper, we