Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.23793 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910974948147200 |
|---|---|
| author | Zheng, Baolin Chen, Guanlin Zhong, Hongqiong Teng, Qingyang Tan, Yingshui Liu, Zhendong Wang, Weixun Liu, Jiaheng Yang, Jian Jing, Huiyun Wei, Jincheng Su, Wenbo Zhu, Xiaoyong Zheng, Bo Zhang, Kaifu |
| author_facet | Zheng, Baolin Chen, Guanlin Zhong, Hongqiong Teng, Qingyang Tan, Yingshui Liu, Zhendong Wang, Weixun Liu, Jiaheng Yang, Jian Jing, Huiyun Wei, Jincheng Su, Wenbo Zhu, Xiaoyong Zheng, Bo Zhang, Kaifu |
| contents | Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models (MLLMs) have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM safety benchmarks, however, fall short in terms of data quality and coverge, and modal risk combinations, resulting in inflated and contradictory evaluation results, which hinders the discovery and governance of security concerns. Besides, we argue that vulnerabilities to harmful queries and oversensitivity to harmless ones should be considered simultaneously in MLLMs safety evaluation, whereas these were previously considered separately. In this paper, to address these shortcomings, we introduce Unified Safety Benchmarks (USB), which is one of the most comprehensive evaluation benchmarks in MLLM safety. Our benchmark features high-quality queries, extensive risk categories, comprehensive modal combinations, and encompasses both vulnerability and oversensitivity evaluations. From the perspective of two key dimensions: risk categories and modality combinations, we demonstrate that the available benchmarks -- even the union of the vast majority of them -- are far from being truly comprehensive. To bridge this gap, we design a sophisticated data synthesis pipeline that generates extensive, high-quality complementary data addressing previously unexplored aspects. By combining open-source datasets with our synthetic data, our benchmark provides 4 distinct modality combinations for each of the 61 risk sub-categories, covering both English and Chinese across both vulnerability and oversensitivity dimensions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23793 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Zheng, Baolin Chen, Guanlin Zhong, Hongqiong Teng, Qingyang Tan, Yingshui Liu, Zhendong Wang, Weixun Liu, Jiaheng Yang, Jian Jing, Huiyun Wei, Jincheng Su, Wenbo Zhu, Xiaoyong Zheng, Bo Zhang, Kaifu Cryptography and Security Artificial Intelligence Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models (MLLMs) have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM safety benchmarks, however, fall short in terms of data quality and coverge, and modal risk combinations, resulting in inflated and contradictory evaluation results, which hinders the discovery and governance of security concerns. Besides, we argue that vulnerabilities to harmful queries and oversensitivity to harmless ones should be considered simultaneously in MLLMs safety evaluation, whereas these were previously considered separately. In this paper, to address these shortcomings, we introduce Unified Safety Benchmarks (USB), which is one of the most comprehensive evaluation benchmarks in MLLM safety. Our benchmark features high-quality queries, extensive risk categories, comprehensive modal combinations, and encompasses both vulnerability and oversensitivity evaluations. From the perspective of two key dimensions: risk categories and modality combinations, we demonstrate that the available benchmarks -- even the union of the vast majority of them -- are far from being truly comprehensive. To bridge this gap, we design a sophisticated data synthesis pipeline that generates extensive, high-quality complementary data addressing previously unexplored aspects. By combining open-source datasets with our synthetic data, our benchmark provides 4 distinct modality combinations for each of the 61 risk sub-categories, covering both English and Chinese across both vulnerability and oversensitivity dimensions. |
| title | USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2505.23793 |