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

ACL ARR 2025 May Submission3629 Authors

Abstract:

**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.

Paper Type: Long

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: data ethics, ethical considerations in NLP applications, policy and governance

Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency

Languages Studied: English, Chinese

Submission Number: 3629