Jailbreaking Multimodal Large Language Models using Multi-Clip Video

• URL: http://arxiv.org/abs/2606.02111v1
• Date: Mon, 01 Jun 2026 11:43:53 GMT
• Title: Jailbreaking Multimodal Large Language Models using Multi-Clip Video
• Abstract summary: We introduce Multi-Clip Video (MCV) SafetyBench, a dataset of 2,920 videos to evaluate how the diversity of video inputs affects the vulnerability of MLLMs.<n> Experiments on eight representative video MLLMs show that attack success consistently increases with the number of clips.<n>Our results indicate that the video modality is (1) more vulnerable than the image modality, (2) more vulnerable to dynamic videos than to static videos, and (3) more vulnerable when videos contain more diverse contexts.
• Score: 2.1309627532459037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As multimodal large language models (MLLMs) have advanced to process video inputs, concerns have emerged about their potential for malicious misuse. Prior jailbreak studies have shown that safety alignment in MLLMs can be bypassed through visual inputs, yet it remains unclear which properties of video inputs induce this vulnerability. To address this gap, we introduce Multi-Clip Video (MCV) SafetyBench, a dataset of 2,920 videos designed to evaluate how the diversity of video inputs affects the vulnerability of MLLMs. Each video consists of multiple short clips depicting diverse contexts related to a harmful query. Experiments on eight representative video MLLMs show that attack success consistently increases with the number of clips. Our results further indicate that the video modality is (1) more vulnerable than the image modality, (2) more vulnerable to dynamic videos than to static videos, and (3) more vulnerable when videos contain more diverse contexts. Building on these findings, we propose a defense strategy that leverages the relative robustness of the image modality.

Related papers

• Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation [1.0012740151280692]
  This paper introduces a framework for evaluating the tri-modal safety of Multimodal Large Language Models (MLLMs)<n>We present the Short-Video Multimodal Adversarial dataset, comprising diverse short-form videos with human-guided synthetic adversarial attacks.<n> Extensive experiments on state-of-the-art MLLMs reveal significant vulnerabilities with high Attack Success Rates (ASR)
  arXiv  Detail & Related papers  (2025-07-16T07:02:15Z)
• Vid-SME: Membership Inference Attacks against Large Video Understanding Models [56.31088116526825]
  We introduce Vid-SME, the first membership inference method tailored for video data used in video understanding models (VULLMs)<n>By leveraging the SME difference between natural and temporally-reversed video frames, Vid-SME derives robust membership scores to determine whether a given video is part of the model's training set.<n> Experiments on various self-trained and open-sourced VULLMs demonstrate the strong effectiveness of Vid-SME.
  arXiv  Detail & Related papers  (2025-05-29T13:17:25Z)
• Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs [45.265397990158846]
  Video-SafetyBench is the first benchmark designed to evaluate the safety of LVLMs under video-text attacks.<n>It comprises 2,264 video-text pairs spanning 48 fine-grained unsafe categories.<n>To generate semantically accurate videos for safety evaluation, we design a controllable pipeline that decomposes video semantics into subject images and motion text.
  arXiv  Detail & Related papers  (2025-05-17T05:06:38Z)
• Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations [48.94868867419852]
  Video-based large language models (video-based LLMs) have achieved impressive performance across various video comprehension tasks.<n>This rapid advancement raises significant privacy and security concerns, particularly regarding the unauthorized use of personal video data.<n>We propose two series of protective video watermarks with imperceptible adversarial perturbations, named Ramblings and Mutes.
  arXiv  Detail & Related papers  (2025-03-26T08:11:58Z)
• Image-based Multimodal Models as Intruders: Transferable Multimodal Attacks on Video-based MLLMs [48.76864299749205]
  Video-based large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks.<n>In this paper, we pioneer an investigation into the transferability of adversarial video samples across V-MLLMs.
  arXiv  Detail & Related papers  (2025-01-02T03:52:22Z)
• Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models [0.0]
  Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data. Attackers can manipulate either the visual or text inputs, or both, to make the model produce unintended or even harmful responses. This paper reviews how visual inputs in MLLMs can be exploited by various attack strategies.
  arXiv  Detail & Related papers  (2024-11-07T16:21:18Z)
• Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs [43.83499677307886]
  Video Watermarking is a technique to protect videos from unauthorized annotations by video-based Large Language Models. Our method preserves the viewing experience while preventing misuse by video-based LLMs.
  arXiv  Detail & Related papers  (2024-07-02T16:34:14Z)
• FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs [57.59518049930211]
  We propose the first adversarial attack tailored for video-based large language models (LLMs) Our attack can effectively induce video-based LLMs to generate incorrect answers when videos are added with imperceptible adversarial perturbations. Our FMM-Attack can also induce garbling in the model output, prompting video-based LLMs to hallucinate.
  arXiv  Detail & Related papers  (2024-03-20T11:05:07Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation [100.23111948079037]
  GPT4Video is a unified multi-model framework that empowers Large Language Models with the capability of both video understanding and generation. Specifically, we develop an instruction-following-based approach integrated with the stable diffusion generative model, which has demonstrated to effectively and securely handle video generation scenarios.
  arXiv  Detail & Related papers  (2023-11-25T04:05:59Z)

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.