Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909735318454272 |
|---|---|
| author | Li, Zuoou Zhang, Weitong Wang, Jingyuan Zhang, Shuyuan Bai, Wenjia Kainz, Bernhard Qiao, Mengyun |
| author_facet | Li, Zuoou Zhang, Weitong Wang, Jingyuan Zhang, Shuyuan Bai, Wenjia Kainz, Bernhard Qiao, Mengyun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09218 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity Li, Zuoou Zhang, Weitong Wang, Jingyuan Zhang, Shuyuan Bai, Wenjia Kainz, Bernhard Qiao, Mengyun Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.09218 |