Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions

arXiv:2501.01872v1 Announce Type: new
Abstract: Despite significant efforts to align large language models with human values and ethical guidelines, these models remain susceptible to sophisticated jailbreak attacks that exploit their reasoning capabilities. Traditional safety mechanisms often focus on detecting explicit malicious intent, leaving deeper vulnerabilities unaddressed. In this work, we introduce a jailbreak technique, POATE (Polar Opposite query generation, Adversarial Template construction, and Elaboration), which leverages contrastive reasoning to elicit unethical responses. POATE generates prompts with semantically opposite intents and combines them with adversarial templates to subtly direct models toward producing harmful responses. We conduct extensive evaluations across six diverse language model families of varying parameter sizes, including LLaMA3, Gemma2, Phi3, and GPT-4, to demonstrate the robustness of the attack, achieving significantly higher attack success rates (~44%) compared to existing methods. We evaluate our proposed attack against seven safety defenses, revealing their limitations in addressing reasoning-based vulnerabilities. To counteract this, we propose a defense strategy that improves reasoning robustness through chain-of-thought prompting and reverse thinking, mitigating reasoning-driven adversarial exploits.



Source link
lol