mlsanityData to 7 Oct 2026

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

arXiv 2501.18628 ↗First posted 27 Jan 2025cs.CR cs.AI cs.CLcited by 0

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 16 of its 36 references that are in the map. First posted on arXiv 27 Jan 2025.

Builds on

16 of 36 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis16 Jun
  2. 2024Distract Large Language Models for Automatic Jailbreak Attack13 Mar
  3. 2024Defending Jailbreak Prompts via In-Context Adversarial Game20 Feb
  4. 2024Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues14 Feb
  5. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
  6. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  7. 2023Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content26 Aug
  8. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 8

  1. 2020Extracting Training Data from Large Language Modelscited by 2,144
  2. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  3. 2024A Survey on Large Language Models for Code Generationcited by 646
  4. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  5. 2023How is ChatGPT's behavior changing over time?cited by 265
  6. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 179
  7. 2024Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)cited by 44
  8. 2023SoK: Technical Implementation and Human Impact of Internet Privacy Regulationscited by 1

Built on by

Not cited yet.