Pith. sign in

REVIEW 10 cited by

HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States

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 2502.14744 v4 pith:UBFUKC2Y submitted 2025-02-20 cs.CL

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

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily focuses on post-hoc alignment techniques, the underlying safety mechanisms within LVLMs remain largely unexplored. In this work , we investigate whether LVLMs inherently encode safety-relevant signals within their internal activations during inference. Our findings reveal that LVLMs exhibit distinct activation patterns when processing unsafe prompts, which can be leveraged to detect and mitigate adversarial inputs without requiring extensive fine-tuning. Building on this insight, we introduce HiddenDetect, a novel tuning-free framework that harnesses internal model activations to enhance safety. Experimental results show that {HiddenDetect} surpasses state-of-the-art methods in detecting jailbreak attacks against LVLMs. By utilizing intrinsic safety-aware patterns, our method provides an efficient and scalable solution for strengthening LVLM robustness against multimodal threats. Our code will be released publicly at https://github.com/leigest519/HiddenDetect.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration

    cs.CR 2026-08 conditional novelty 6.0 of 10

    Safety failures in multimodal LLMs happen because unsafe image-plus-text inputs shift internal representations past a still-working refusal boundary, and a representation-calibration fine-tune restores refusal with un...

  2. V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Video LLMs understand harmful content but activate weaker refusal signals when the query is benign; prompt realignment reduces attack success from ~48% to ~1%.

  3. Breaking Refusal in the First Half: A Mechanistic Study of the Prefill Jailbreak

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Refusal under a prefill jailbreak is a shallow response-site computation: the harm representation stays intact, the failure lives in an early response window, and the dominant mechanism is passive autoregressive conditioning.

  4. Adaptively Robust LLM Monitoring via Activation Watermarking

    cs.CR 2026-03 conditional novelty 6.0 of 10

    Activation Watermarking embeds a secret keyed direction in an LLM's hidden states so policy-violating responses can be detected by a cosine test, cutting adaptive-jailbreak evasion relative to guard models.

  5. The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair

    cs.LG 2025-08 reject novelty 6.0 of 10

    The submission's abstract announces a differentiable microLED repair planner, yet its full text is the LoD jailbreak-detection paper (arXiv 2508.09201v4), leaving the claimed result without any derivation.

  6. Learning Efficient Robotic Garment Manipulation with Standardization

    cs.RO 2025-06 conditional novelty 6.0 of 10

    APS-Net combines fling and pick-and-place actions to unfold and standardize garments, achieving better coverage, alignment, and real-world folding success than earlier methods.

  7. Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models

    cs.AI 2025-05 conditional novelty 6.0 of 10

    A new benchmark shows that top reasoning models identify all relevant risks in under 40% of cases even when their final answers look safe.

  8. USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

    cs.CR 2025-05 conditional novelty 6.0 of 10

    USB-SafeBench is a unified MLLM safety benchmark with 61 risk categories, 4 modality combinations, and dual-language vulnerability and oversensitivity tests.

  9. The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions

    cs.CL 2025-02 conditional novelty 6.0 of 10

    Safety refusal in Llama 3.1 8B is governed by a dominant activation direction plus smaller interpretable directions, and removing prompt tokens that activate these secondary directions can bypass fine-tuned safety.

  10. Language-Guided Long Horizon Manipulation with LLM-based Planning and Visual Perception

    cs.RO 2025-09 conditional novelty 5.0 of 10

    A robot folds cloth from spoken language by decomposing instructions with GPT-4o and grounding each step with a SigLIP2-based pick-and-place perception module.

Pith tools