SafeMT: Multi-turn Safety for Multimodal Language Models

• URL: http://arxiv.org/abs/2510.12133v1
• Date: Tue, 14 Oct 2025 04:24:07 GMT
• Title: SafeMT: Multi-turn Safety for Multimodal Language Models
• Authors: Han Zhu, Juntao Dai, Jiaming Ji, Haoran Li, Chengkun Cai, Pengcheng Wen, Chi-Min Chan, Boyuan Chen, Yaodong Yang, Sirui Han, Yike Guo,
• Abstract summary: We introduce SafeMT, a benchmark that features dialogues of varying lengths generated from harmful queries accompanied by images.<n>This benchmark consists of 10,000 samples in total, encompassing 17 different scenarios and four jailbreak methods.<n>We assess the safety of 17 models using this benchmark and discover that the risk of successful attacks on these models increases as the number of turns in harmful dialogues rises.<n>We propose a dialogue safety moderator capable of detecting malicious intent concealed within conversations and providing MLLMs with relevant safety policies.
• Score: 42.59582247058264
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interactions, pose a greater risk than single prompts; however, existing benchmarks do not adequately consider this situation. To encourage the community to focus on the safety issues of these models in multi-turn dialogues, we introduce SafeMT, a benchmark that features dialogues of varying lengths generated from harmful queries accompanied by images. This benchmark consists of 10,000 samples in total, encompassing 17 different scenarios and four jailbreak methods. Additionally, we propose Safety Index (SI) to evaluate the general safety of MLLMs during conversations. We assess the safety of 17 models using this benchmark and discover that the risk of successful attacks on these models increases as the number of turns in harmful dialogues rises. This observation indicates that the safety mechanisms of these models are inadequate for recognizing the hazard in dialogue interactions. We propose a dialogue safety moderator capable of detecting malicious intent concealed within conversations and providing MLLMs with relevant safety policies. Experimental results from several open-source models indicate that this moderator is more effective in reducing multi-turn ASR compared to existed guard models.

Related papers

• MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues [39.24594135913578]
  We introduce the Multi-Turn Multimodal Contextual Safety Benchmark (MTMCS-Bench), a benchmark of realistic images and multi-turn conversations.<n>MTMCS-Bench offers paired safe and unsafe dialogues with structured evaluation.<n>We observe persistent trade-offs between contextual safety and utility, with models tending to either miss gradual risks or over-refuse benign dialogues.
  arXiv  Detail & Related papers  (2026-01-11T03:10:56Z)
• When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life [36.244977974241245]
  We investigate and evaluate the safety impact of Multimodal Large Language Models (MLLMs) on human behavior in daily life.<n>We introduce SaLAD, a multimodal safety benchmark which contains 2,013 real-world image-text samples.<n>Results on 18 MLLMs demonstrate that the top-performing models achieve a safe response rate of only 57.2% on unsafe queries.
  arXiv  Detail & Related papers  (2026-01-07T15:59:07Z)
• OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models [54.80460603255789]
  We introduce OutSafe-Bench, the first most comprehensive content safety evaluation test suite designed for the multimodal era.<n>OutSafe-Bench includes a large-scale dataset that spans four modalities, featuring over 18,000 bilingual (Chinese and English) text prompts, 4,500 images, 450 audio clips and 450 videos, all systematically annotated across nine critical content risk categories.<n>In addition to the dataset, we introduce a Multidimensional Cross Risk Score (MCRS), a novel metric designed to model and assess overlapping and correlated content risks across different categories.
  arXiv  Detail & Related papers  (2025-11-13T13:18:27Z)
• LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models [1.4923957493548121]
  Malicious intent can be spread across turns and images in Multimodal Multi-Turn (MMT) dialogues.<n>We present the first systematic definition and study of MMT dialogue safety.<n>We develop an automated multimodal multi-turn red-teaming framework to generate unsafe multi-turn dialogues for MMDS.<n>We present LLaVAShield, a powerful tool that jointly detects and assesses risk in user inputs and assistant responses.
  arXiv  Detail & Related papers  (2025-09-30T07:42:23Z)
• Automating Steering for Safe Multimodal Large Language Models [58.36932318051907]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)
• Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs [56.440345471966666]
  Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images.<n>This paper introduces MMSafeAware, the first comprehensive multimodal safety awareness benchmark designed to evaluate MLLMs across 29 safety scenarios.<n> MMSafeAware includes both unsafe and over-safety subsets to assess models abilities to correctly identify unsafe content and avoid over-sensitivity that can hinder helpfulness.
  arXiv  Detail & Related papers  (2025-02-16T16:12:40Z)
• SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks [46.25325034315104]
  We propose a fine-grained benchmark SafeDialBench for evaluating the safety of Large Language Models (LLMs)<n>Specifically, we design a two-tier hierarchical safety taxonomy that considers 6 safety dimensions and generates more than 4000 multi-turn dialogues in both Chinese and English under 22 dialogue scenarios.<n> Notably, we construct an innovative assessment framework of LLMs, measuring capabilities in detecting, and handling unsafe information and maintaining consistency when facing jailbreak attacks.
  arXiv  Detail & Related papers  (2025-02-16T12:08:08Z)
• Multimodal Situational Safety [73.63981779844916]
  We present the first evaluation and analysis of a novel safety challenge termed Multimodal Situational Safety.<n>For an MLLM to respond safely, whether through language or action, it often needs to assess the safety implications of a language query within its corresponding visual context.<n>We develop the Multimodal Situational Safety benchmark (MSSBench) to assess the situational safety performance of current MLLMs.
  arXiv  Detail & Related papers  (2024-10-08T16:16:07Z)

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.