相关论文: HQA-VLAttack: Towards High Quality Adversarial Att…

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…

Video Multimodal Large Language Models (V-MLLMs) have shown impressive capabilities in temporal reasoning and cross-modal understanding, yet their vulnerability to adversarial attacks remains underexplored due to unique challenges: complex…

Adversarial examples have posed a severe threat to deep neural networks due to their transferable nature. Currently, various works have paid great efforts to enhance the cross-model transferability, which mostly assume the substitute model…

Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples.…

Transfer-based adversarial example is one of the most important classes of black-box attacks. However, there is a trade-off between transferability and imperceptibility of the adversarial perturbation. Prior work in this direction often…

We propose a novel framework for real-time black-box universal attacks which disrupts activations of early convolutional layers in deep learning models. Our hypothesis is that perturbations produced in the wavelet space disrupt early…

Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key aspects of VL tasks: multimodal attacks, where both image…

The deep neural network (DNN) models for object detection using camera images are widely adopted in autonomous vehicles. However, DNN models are shown to be susceptible to adversarial image perturbations. In the existing methods of…

Language models based on deep neural networks are vulnerable to textual adversarial attacks. While rich-resource languages like English are receiving focused attention, Tibetan, a cross-border language, is gradually being studied due to its…

Research on adversarial attacks are becoming widely popular in the recent years. One of the unexplored areas where prior research is lacking is the effect of adversarial attacks on code-mixed data. Therefore, in the present work, we have…

Image Quality Assessment (IQA) and Image Aesthetic Assessment (IAA) aim to simulate human subjective perception of image visual quality and aesthetic appeal. Despite distinct learning objectives, they have underlying interconnectedness due…

Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…

Medical Visual Question Answering (VQA) is an important challenge, as it would lead to faster and more accurate diagnoses and treatment decisions. Most existing methods approach it as a multi-class classification problem, which restricts…

Visual reinforcement learning has achieved remarkable progress in visual control and robotics, but its vulnerability to adversarial perturbations remains underexplored. Most existing black-box attacks focus on vector-based or…

Recently in robotics, Vision-Language-Action (VLA) models have emerged as a transformative approach, enabling robots to execute complex tasks by integrating visual and linguistic inputs within an end-to-end learning framework. Despite their…

Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rates or fail to search efficiently in the exponentially large…

Vision-language models (VLMs) have made significant progress in recent visual-question-answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However, are these models truly effective? In this work, we show that VLMs…

Document Visual Question Answering (DocVQA) enables end-to-end reasoning grounded on information present in a document input. While recent models have shown impressive capabilities, they remain vulnerable to adversarial attacks. In this…

Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this…

Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…