相关论文: When and Where to Attack? Stage-wise Attention-Gui…

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

A line of recent training-free methods for mitigating hallucinations in large vision-language models (LVLMs) operates by amplifying attention to visual tokens during autoregressive generation within a single forward pass. We refer to this…

The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against…

Large language models (LLMs) have revolutionized various applications, making robust safety alignment essential to prevent harmful outputs. Current safety alignment techniques, however, harbor inherent vulnerabilities due to their reliance…

Vision-language models (VLMs) rely on a shared visual-textual representation space to perform tasks such as zero-shot classification, image captioning, and visual question answering (VQA). While this shared space enables strong cross-task…

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…

Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual information. This paper presents a comprehensive analysis of…

Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights are made public, they are exposed to jailbreak attacks even after alignment. Existing…

Current safety alignment for large language models(LLMs) continues to present vulnerabilities, given that adversarial prompting can effectively bypass their safety measures.Our investigation shows that these safety mechanisms predominantly…

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual…

With the rapid development of the Vision-Language Model (VLM), significant progress has been made in Visual Question Answering (VQA) tasks. However, existing VLM often generate inaccurate answers due to a lack of up-to-date knowledge. To…

Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models and manipulate black-box VLM outputs. Prior targeted transfer attacks often overfit…

The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…

We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries and even multiple models. By backpropagating through the…

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus…

A triangular mesh is one of the most popular 3D data representations. As such, the deployment of deep neural networks for mesh processing is widely spread and is increasingly attracting more attention. However, neural networks are prone to…

As the study of graph neural networks becomes more intensive and comprehensive, their robustness and security have received great research interest. The existing global attack methods treat all nodes in the graph as their attack targets.…

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model…

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,…

The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…