Pith. sign in

REVIEW 2 cited by

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) 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 2505.22271 v1 pith:PRTKP5AX submitted 2025-05-28 cs.CR cs.AIcs.CL

classification cs.CRcs.AIcs.CL
keywords jailbreakattacksdefensefine-tuningllmsmultimodaladversarialdefend
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While (multimodal) large language models (LLMs) have attracted widespread attention due to their exceptional capabilities, they remain vulnerable to jailbreak attacks. Various defense methods are proposed to defend against jailbreak attacks, however, they are often tailored to specific types of jailbreak attacks, limiting their effectiveness against diverse adversarial strategies. For instance, rephrasing-based defenses are effective against text adversarial jailbreaks but fail to counteract image-based attacks. To overcome these limitations, we propose a universal defense framework, termed Test-time IMmunization (TIM), which can adaptively defend against various jailbreak attacks in a self-evolving way. Specifically, TIM initially trains a gist token for efficient detection, which it subsequently applies to detect jailbreak activities during inference. When jailbreak attempts are identified, TIM implements safety fine-tuning using the detected jailbreak instructions paired with refusal answers. Furthermore, to mitigate potential performance degradation in the detector caused by parameter updates during safety fine-tuning, we decouple the fine-tuning process from the detection module. Extensive experiments on both LLMs and multimodal LLMs demonstrate the efficacy of TIM.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    DDRL reduces spurious reward noise in test-time RL for math by excluding ambiguous samples, using fixed advantages, and adding consensus-based updates, outperforming prior TTRL methods on math benchmarks.

  2. On the Vulnerability of Parameter-Level Defenses to Model Merging

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    Parameter-level defenses for model merging are vulnerable to Anchor-Guided Attack because protected weights are dominated by the pretrained model, and a new defense ARF is introduced to counter it.

Pith tools