Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity

• URL: http://arxiv.org/abs/2508.09218v1
• Date: Mon, 11 Aug 2025 18:57:55 GMT
• Title: Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity
• Abstract summary: Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks.<n> MLLMs are vulnerable to adversarial prompts as safety mechanisms fail to prevent the generation of harmful outputs.<n>We introduce a four-axis evaluation framework that considers input on-topicness, input out-of-distribution (OOD) intensity, output harmfulness, and output refusal rate.
• Score: 24.809329513705915
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful outputs. Although recent jailbreak strategies report high success rates, many responses classified as "successful" are actually benign, vague, or unrelated to the intended malicious goal. This mismatch suggests that current evaluation standards may overestimate the effectiveness of such attacks. To address this issue, we introduce a four-axis evaluation framework that considers input on-topicness, input out-of-distribution (OOD) intensity, output harmfulness, and output refusal rate. This framework identifies truly effective jailbreaks. In a substantial empirical study, we reveal a structural trade-off: highly on-topic prompts are frequently blocked by safety filters, whereas those that are too OOD often evade detection but fail to produce harmful content. However, prompts that balance relevance and novelty are more likely to evade filters and trigger dangerous output. Building on this insight, we develop a recursive rewriting strategy called Balanced Structural Decomposition (BSD). The approach restructures malicious prompts into semantically aligned sub-tasks, while introducing subtle OOD signals and visual cues that make the inputs harder to detect. BSD was tested across 13 commercial and open-source MLLMs, where it consistently led to higher attack success rates, more harmful outputs, and fewer refusals. Compared to previous methods, it improves success rates by $67\%$ and harmfulness by $21\%$, revealing a previously underappreciated weakness in current multimodal safety systems.

Related papers

• SoK: Robustness in Large Language Models against Jailbreak Attacks [18.3385249246391]
  Large Language Models (LLMs) have achieved remarkable success but remain highly susceptible to jailbreak attacks.<n>Such attacks pose real-world risks, eroding safety, trust, and regulatory compliance in high-stakes applications.<n>We present a systematic taxonomy of jailbreak attacks and defenses and introduce Security Cube, a unified, multi-dimensional framework for comprehensive evaluation of these techniques.
  arXiv  Detail & Related papers  (2026-05-06T15:53:17Z)
• Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography [77.44136793431893]
  We propose a novel jailbreak paradigm that introduces dual steganography to covertly embed malicious queries into benign-looking images.<n>Our Odysseus successfully jailbreaks several pioneering and realistic MLLM-integrated systems, achieving up to 99% attack success rate.
  arXiv  Detail & Related papers  (2025-12-23T08:53:36Z)
• Why does weak-OOD help? A Further Step Towards Understanding Jailbreaking VLMs [62.03547713936256]
  Large Vision-Language Models (VLMs) are susceptible to jailbreak attacks.<n>This paper advances the in-depth understanding of OOD-based VLM jailbreak methods.
  arXiv  Detail & Related papers  (2025-11-11T15:46:44Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs [83.11815479874447]
  We propose a novel jailbreak attack framework, inspired by cognitive decomposition and biases in human cognition.<n>We employ cognitive decomposition to reduce the complexity of malicious prompts and relevance bias to reorganize prompts.<n>We also introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm.
  arXiv  Detail & Related papers  (2025-05-03T05:28:11Z)
• Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy [31.03584769307822]
  We propose JOOD, a new Jailbreak framework via OOD-ifying inputs beyond the safety alignment.<n>Experiments across diverse jailbreak scenarios demonstrate that JOOD effectively jailbreaks recent proprietary LLMs and MLLMs.
  arXiv  Detail & Related papers  (2025-03-26T01:25:24Z)
• Foot-In-The-Door: A Multi-turn Jailbreak for LLMs [40.958137601841734]
  A key challenge is jailbreak, where adversarial prompts bypass built-in safeguards to elicit harmful disallowed outputs.<n>Inspired by psychological foot-in-the-door principles, we introduce FITD,a novel multi-turn jailbreak method.<n>Our approach progressively escalates the malicious intent of user queries through intermediate bridge prompts and aligns the model's response by itself to induce toxic responses.
  arXiv  Detail & Related papers  (2025-02-27T06:49:16Z)
• Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense [55.77152277982117]
  We introduce Layer-AdvPatcher, a methodology designed to defend against jailbreak attacks.<n>We use an unlearning strategy to patch specific layers within large language models through self-augmented datasets.<n>Our framework reduces the harmfulness and attack success rate of jailbreak attacks.
  arXiv  Detail & Related papers  (2025-01-05T19:06:03Z)
• Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions [51.51850981481236]
  We introduce POATE, a novel jailbreak technique that harnesses contrastive reasoning to provoke unethical responses.<n>PoATE crafts semantically opposing intents and integrates them with adversarial templates, steering models toward harmful outputs with remarkable subtlety.<n>To counter this, we propose Intent-Aware CoT and Reverse Thinking CoT, which decompose queries to detect malicious intent and reason in reverse to evaluate and reject harmful responses.
  arXiv  Detail & Related papers  (2025-01-03T15:40:03Z)
• Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level [10.476222570886483]
  Large language models (LLMs) have demonstrated immense utility across various industries.<n>As LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts.<n>This paper examines the LLMs' capability to recognize harmful outputs, revealing and quantifying their proficiency in assessing the danger of previous tokens.
  arXiv  Detail & Related papers  (2024-10-09T12:09:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.