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

Authors: Junchen Ding, Jiahao Zhang, Yi Liu, Ziqi Ding, Gelei Deng, Yuekang Li
Published: 2025-01-27 | Updated: 2025-08-25

Source: https://arxiv.org/abs/2501.18628

PDF: https://arxiv.org/pdf/2501.18628

AIにより推定されたラベル

プロンプトインジェクション 脱獄手法 プロンプトリーキング

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

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 against defence mechanisms. Our findings highlight critical vulnerabilities in existing LLM safeguards, underscoring the need for more robust safety defences.