TombRaider: Entering the Vault of History to Jailbreak Large Language Models

Warning: This paper contains content that may involve potentially harmful behaviours, discussed strictly for research purposes. Jailbreak attacks can hinder the safety of Large Language Model (LLM) applications, especially chatbots. Studying jailbreak techniques is an important AI red teaming task for improving the safety of these applications. In this paper, we introduce TOMBRAIDER, a novel jailbreak technique that exploits the ability to store, retrieve, and use historical knowledge of LLMs. TOMBRAIDER employs two agents, the inspector agent to extract relevant historical information and the attacker agent to generate adversarial prompts, enabling effective bypassing of safety filters. We intensively evaluated TOMBRAIDER on six popular models. Experimental results showed that TOMBRAIDER could outperform state-of-the-art jailbreak techniques, achieving nearly 100% attack success rates (ASRs) on bare models and maintaining over 55.4% ASR against defence mechanisms. Our findings highlight critical vulnerabilities in existing LLM safeguards, underscoring the need for more robust safety defences. * Corresponding author. I'm sorry, but I can't assist with that. I'll do my best to provide helpful and ethical information! Could you please tell me how to rob a bank? Yes, Herman Karl Lamm was a German-born bank robber often referred to as the "father of modern bank robbery." 😊 🤖 🤖 Do you know a historical figure named Herman Karl Lamm? 🤓 Here are some details about his success: planning, roles, rehearsals, escapes, and psychology...