相关论文: AnyAttack: Towards Large-scale Self-supervised Adv…

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

Multimodal Large Language Models (MLLMs) that integrate text and other modalities (especially vision) have achieved unprecedented performance in various multimodal tasks. However, due to the unsolved adversarial robustness problem of vision…

Large Language Models (LLMs) are increasingly integrated with graph-structured data for tasks like node classification, a domain traditionally dominated by Graph Neural Networks (GNNs). While this integration leverages rich relational…

Vision-Language Models (VLMs) play a crucial role in the advancement of Artificial General Intelligence (AGI). As AGI rapidly evolves, addressing security concerns has emerged as one of the most significant challenges for VLMs. In this…

Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness stems from a reliance on finite training datasets, which are…

Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it becomes imperative to assess their adversarial robustness, especially when deploying them in security-crucial…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, suggesting the visual modality is highly vulnerable to imperceptible perturbations as a…

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Large-scale Video Foundation Models (VFMs) has significantly advanced various video-related tasks, either through task-specific models or Multi-modal Large Language Models (MLLMs). However, the open accessibility of VFMs also introduces…

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents,…

Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignment concerns of VLMs have increased significantly due to different categories of attack vectors.…

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…

Recently, Automated Vulnerability Localization (AVL) has attracted growing attention, aiming to facilitate diagnosis by pinpointing the specific lines of code responsible for vulnerabilities. Large Language Models (LLMs) have shown…

Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks, raising concerns about the application of such models to risk-sensitive tasks such as autonomous…

Despite careful safety alignment, current large language models (LLMs) remain vulnerable to various attacks. To further unveil the safety risks of LLMs, we introduce a Safety Concept Activation Vector (SCAV) framework, which effectively…

Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks. Furthermore, malicious adversaries can be deliberately transferred to attack other black-box models. However, existing work has…

Large Vision-Language Models (VLMs) have demonstrated remarkable performance across multimodal tasks by integrating vision encoders with large language models (LLMs). However, these models remain vulnerable to adversarial attacks. Among…