Related papers: SAM Meets UAP: Attacking Segment Anything Model Wi…
Deep recognition models are widely vulnerable to adversarial examples, which change the model output by adding quasi-imperceptible perturbation to the image input. Recently, Segment Anything Model (SAM) has emerged to become a popular…
The previous study has shown that universal adversarial attacks can fool deep neural networks over a large set of input images with a single human-invisible perturbation. However, current methods for universal adversarial attacks are based…
Recently, with the application of deep learning in the remote sensing image (RSI) field, the classification accuracy of the RSI has been dramatically improved compared with traditional technology. However, even the state-of-the-art object…
The Segment Anything Model (SAM) is a foundation model for general image segmentation. Although it exhibits impressive performance predominantly on natural images, understanding its robustness against various image perturbations and domains…
Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to process multiple images as inputs. However, the vulnerabilities of multi-image MLLMs…
Recent studies reveal the vulnerability of the image segmentation foundation model SAM to adversarial examples. Its successor, SAM2, has attracted significant attention due to its strong generalization capability in video segmentation.…
Universal Adversarial Perturbations (UAPs) are imperceptible, image-agnostic vectors that cause deep neural networks (DNNs) to misclassify inputs with high probability. In practical attack scenarios, adversarial perturbations may undergo…
The Segment Anything Model (SAM) is a widely used vision foundation model with diverse applications, including image segmentation, detection, and tracking. Given SAM's wide applications, understanding its robustness against adversarial…
Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications. However, existing adversarial detection methods require access to sufficient training data, which brings…
The emergence of large models, also known as foundation models, has brought significant advancements to AI research. One such model is Segment Anything (SAM), which is designed for image segmentation tasks. However, as with other foundation…
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…
Multiple convolutional neural network (CNN) classifiers have been proposed for electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, CNN models have been found vulnerable to universal adversarial perturbations (UAPs),…
While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…
Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking…
The Segment Anything Model (SAM) is a cornerstone of image segmentation, demonstrating exceptional performance across various applications, particularly in autonomous driving and medical imaging, where precise segmentation is crucial.…
Text-to-Image (T2I) models have advanced significantly, but their growing popularity raises security concerns due to their potential to generate harmful images. To address these issues, we propose UPAM, a novel framework to evaluate the…
Adversarial attacks against deep learning-based object detectors have been studied extensively in the past few years. Most of the attacks proposed have targeted the model's integrity (i.e., caused the model to make incorrect predictions),…
Recent advances in diffusion models have enabled powerful image editing capabilities guided by natural language prompts, unlocking new creative possibilities. However, they introduce significant ethical and legal risks, such as deepfakes…
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks…
We introduce Universal and Transferable Adversarial Perturbations (UTAP) for pathology foundation models that reveal critical vulnerabilities in their capabilities. Optimized using deep learning, UTAP comprises a fixed and weak noise…