This work proposes a novel information overloading method that is equipped with both extensive text and multi-dimensional image attacks, underscoring the need for stronger defenses against complex multimodal jailbreak inputs.
Abstract
Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as personal assistants, document analysis systems, and embodied agents. However, their dual-modal attack surfaces make them vulnerable to jailbreak attacks. Existing LVLM jailbreaks rely on simple designs, e.g., short text and out-of-distribution images. Nevertheless, recent advancements in both large language model backbones and multimodal mechanisms undermine these attacks, particularly their transferability among model architectures. To overcome this limitation, we propose a novel information overloading method that is equipped with both extensive text and multi-dimensional image attacks. These components are arranged in recursion-based image-typography layouts to exponentially increase multimodal information complexity. This overloading approach amplifies the cross-modal processing required, which undermines the safety alignment in LVLMs. Extensive experiments on both open-sourced and commercial LVLMs establish our method as a new state-of-the-art LVLM jailbreak attack. On open-source models, our method achieves an average ASR of 88.6%; on commercial LVLMs, it reaches an average ASR of 84.0%, exceeding the best baseline by 48.7%. Moreover, our prompts optimized on open-source surrogate models transfer effectively across model families. Beyond empirical results, we probe the safety-critical information flows within victim LVLMs. Our observations reveal that complex image-typography compositions induce intensified cross-modal processing and reduce the model's certainty in generating refusal responses. Together, these findings highlight information overloading as a practical and emerging safety risk for real-world LVLM deployments, underscoring the need for stronger defenses against complex multimodal jailbreak inputs.
Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and image-based jailbreaks, video jailbreaks against LVLMs remain largely unexplored. Existing video jailbreak methods mainly manipulate textual content embedded in videos, while overlooking how such information is organized over time. Our analysis reveals that jailbreak effectiveness depends not only on the semantics of textual information but also on its temporal presentation, including duration and timing-slot allocation. Motivated by this finding, we use subtitles, which are common in real-world videos and allow semantic content to be presented under precise temporal control without appearing visually intrusive, as a natural attack medium. Based on this insight, we propose TempJail, a black-box video-based jailbreak framework that constructs query-aligned dialogue-style subtitle sequences and optimizes their temporal scheduling to exploit temporal vulnerabilities in LVLMs and elicit responses that satisfy the harmful intent of the source query. Extensive experiments on four representative LVLMs and two datasets demonstrate that TempJail achieves the highest attack success rate across all evaluated model--dataset settings, outperforming the strongest baseline by 53 and 18 percentage points in dataset-averaged ASR on GPT-5 and Gemini 3.5-Flash, respectively.
Ling Zhou, Yihao Huang, Jinglin Sun et al.· 0 citations
Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information. While existing benchmarks have laid a solid foundation for evaluation, they are often static, resource-intensive to build, and limited in adaptability. In comparison, automatic evaluation has shown promise in the textual domain, but the visual modality remains far less explored. To advance this frontier, in this work, we introduce AutoDavis, a first-of-its-kind automatic and dynamic evaluation protocol that enables on-demand benchmarking of LVLMs across specific capability dimensions. AutoDavis leverages text-to-image models to generate relevant image samples and then utilizes LVLMs to orchestrate visual question-answering (VQA) tasks, completing the evaluation process efficiently and flexibly. To ensure data diversity, our framework employs a hierarchical aspect-driven generation process enhanced with semantic graph-based constraints. To safeguard reliability, the framework incorporates a self-validation mechanism to detect and correct errors, along with an error-driven adjustment module to mitigate potential bias. Through an extensive evaluation of 11 popular LVLMs across five demanded user inputs (i.e., evaluation capabilities), the framework shows effectiveness and reliability, offering a new paradigm for dynamic benchmarking of multimodal intelligence. View website for code and data.
Han Bao, Yue Huang, Yanbo Wang et al.· Proceedings of the 32nd ACM...· 0 citations
This paper identifies three previously overlooked issues caused by inappropriate cross-modal interactions and excessive operations in the Simple Vision-Language Attack (SimVLA) pipeline, and proposes the SimVLA, which observably improves transferability and efficiency.
Yuchen Ren, Zhengyu Zhao, Chenhao Lin et al.· IEEE Transactions on Informa...· 0 citations
Vision LLMs are trained on vast datasets containing paired image-text samples, allowing them to perform tasks such as image captioning, visual question answering (VQA) and multimodal reasoning. These Models (Vision LLMs) mark a transformative leap in artificial intelligence by merging visual and linguistic understanding, enabling seamless human-machine communication, power groundbreaking applications-from automated diagnostic reporting in healthcare to real-time scene analysis in autonomous systems. Yet, key challenges remain, including computational inefficiency, embedded biases in training data and limited interpretability which currently restrict broader deployment. Cutting-edge research is tackling these obstacles through optimized model architectures, fairness-aware dataset curation and advanced explainable AI methods. As these advancements progress, Vision LLMs are poised to revolutionize AI- driven solutions across industries such as healthcare, robotics, autonomous vehicles. Their continued evolution is redefining the landscape of interdisciplinary AI, fostering more intuitive, ethical and scalable intelligent systems. This article provides an overview of Vision LLM architectures, their applications and the challenges they face and case study of how building of AI Models through visionLLM may help IndoAI AI camera system.
Rohit Yadav· Journal of Artificial Intell...· 0 citations
It is suggested that multimodal safety cannot be enforced reliably without modeling the requested operation, the visual target to which it applies, and the confidence of that grounding.
Large language models (LLMs) are built on the classic Transformer architecture and have become a core driving force for the rapid development of modern artificial intelligence. This paper presents a systematic review of LLMs, elaborating on their fundamental working principles, mainstream open-source models, effective lightweight optimization methods, retrieval-augmented generation frameworks and key human-value-aligned technologies. Nowadays, LLMs have been widely applied in practice. Typical scenarios include intelligent text generation, professional knowledge-based question answering and automated code generation, delivering remarkable value to both industries and academia. However, their large-scale industrial application is still restricted by multiple challenges. The major issues involve content hallucination, poor model interpretability, excessive computing resource consumption, potential ethical risks and unsatisfactory multimodal integration capability. This paper also forecasts the future development directions of LLMs, such as lightweight deployment on edge devices, safety-focused human value alignment, in-depth cross-modal fusion and customized large models for vertical industries. Additionally, it collects a number of representative cases, which can offer solid references and practical guidance for relevant researchers and engineering practitioners to carry out further studies.