Pith. sign in

REVIEW 4 cited by

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.11459 v1 pith:4VQMBQXL submitted 2024-10-15 cs.CL

classification cs.CL
keywords harmfuljailbreakllmsquestionsmodelsmulti-turnadvancedattack
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have exhibited outstanding performance in engaging with humans and addressing complex questions by leveraging their vast implicit knowledge and robust reasoning capabilities. However, such models are vulnerable to jailbreak attacks, leading to the generation of harmful responses. Despite recent research on single-turn jailbreak strategies to facilitate the development of defence mechanisms, the challenge of revealing vulnerabilities under multi-turn setting remains relatively under-explored. In this work, we propose Jigsaw Puzzles (JSP), a straightforward yet effective multi-turn jailbreak strategy against the advanced LLMs. JSP splits questions into harmless fractions as the input of each turn, and requests LLMs to reconstruct and respond to questions under multi-turn interaction. Our experimental results demonstrate that the proposed JSP jailbreak bypasses original safeguards against explicitly harmful content, achieving an average attack success rate of 93.76% on 189 harmful queries across 5 advanced LLMs (Gemini-1.5-Pro, Llama-3.1-70B, GPT-4, GPT-4o, GPT-4o-mini). Moreover, JSP achieves a state-of-the-art attack success rate of 92% on GPT-4 on the harmful query benchmark, and exhibits strong resistant to defence strategies. Warning: this paper contains offensive examples.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

    cs.CR 2025-08 conditional novelty 6.0 of 10

    ASTRA is an automated red-teaming agent that uses knowledge-graph-guided spatial and temporal probing to find 11-66% more safety violations in AI coding assistants than existing tools.

  2. RedCoder: Automated Multi-Turn Red Teaming for Code LLMs

    cs.SE 2025-06 conditional novelty 6.0 of 10

    A multi-turn red-teaming agent trained on simulated attacker-defender conversations induces vulnerable code at higher rates than prior attack methods across several code LLMs.

  3. Towards terahertz nanomechanics

    physics.app-ph 2025-08 unverdicted novelty 5.0 of 10

    Suspended Lamb-wave resonators in lithium niobate films thinned from 300 nm to 67 nm reach 220 GHz, doubling the prior record.

  4. Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM

    cs.CL 2025-08 unverdicted novelty 3.0 of 10

    The submission's abstract promises an LLM safety survey, but the provided body is the opening page of an unrelated arithmetic-dynamics paper, so the artifact is internally inconsistent.

Pith tools