相关论文: Adversarial Robustness of Vision in Open Foundatio…

Adversarial examples derived from deliberately crafted perturbations on visual inputs can easily harm decision process of deep neural networks. To prevent potential threats, various adversarial training-based defense methods have grown…

The growing reliance on deep learning models in safety-critical domains such as healthcare and autonomous navigation underscores the need for defenses that are both robust to adversarial perturbations and transparent in their…

To develop trustworthy Vision-Language Models (VLMs), it is essential to address adversarial robustness and hallucination mitigation, both of which impact factual accuracy in high-stakes applications such as defense and healthcare. Existing…

Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…

Vision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on perturbations that manifest as unusual textures rarely…

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…

Medical visual question answering (VQA) bridges the gap between visual information and clinical decision-making, enabling doctors to extract understanding from clinical images and videos. In particular, surgical VQA can enhance the…

The integration of visual and textual data in Vision-Language Pre-training (VLP) models is crucial for enhancing vision-language understanding. However, the adversarial robustness of these models, especially in the alignment of image-text…

The rapid expansion of research on Large Language Model (LLM) safety and robustness has produced a fragmented and oftentimes buggy ecosystem of implementations, datasets, and evaluation methods. This fragmentation makes reproducibility and…

Vision-Language Models (VLMs) have achieved remarkable success in various tasks, yet their robustness to real-world illumination variations remains largely unexplored. To bridge this gap, we propose \textbf{I}llumination…

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…

Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…

The 2D object detection in clean images has been a well studied topic, but its vulnerability against adversarial attack is still worrying. Existing work has improved robustness of object detectors by adversarial training, at the same time,…

Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such…

Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have…

Vision-Language-Action (VLA) models are driving rapid progress in robotics by enabling agents to interpret multimodal inputs and execute complex, long-horizon tasks. However, their safety and robustness against adversarial attacks remain…

In this paper, we ask whether Vision Transformers (ViTs) can serve as an underlying architecture for improving the adversarial robustness of machine learning models against evasion attacks. While earlier works have focused on improving…

There exists a vast number of adversarial attacks and defences for machine learning algorithms of various types which makes assessing the robustness of algorithms a daunting task. To make matters worse, there is an intrinsic bias in these…

Recently, large multimodal models (LMMs) have achieved significant advancements. When dealing with high-resolution images, dominant LMMs typically divide them into multiple local images and a global image, leading to a large number of…