Related papers: SAM Meets UAP: Attacking Segment Anything Model Wi…
Diffusion models have revolutionized customized text-to-image generation, allowing for efficient synthesis of photos from personal data with textual descriptions. However, these advancements bring forth risks including privacy breaches and…
Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these…
The Segment-Anything Model (SAM) is a vision foundation model for segmentation with a prompt-driven framework. SAM generates class-agnostic masks based on user-specified instance-referring prompts. However, adapting SAM for automated…
Segment Anything Model (SAM), a new AI model from Meta AI released in April 2023, is an ambitious tool designed to identify and separate individual objects within a given image through semantic interpretation. The advanced capabilities of…
Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing methods present…
We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations. Specifically, we show that targeted UAPs generated by projected gradient descent exhibit two human-aligned…
Segment Anything Model (SAM) has recently achieved amazing results in the field of natural image segmentation. However, it is not effective for medical image segmentation, owing to the large domain gap between natural and medical images. In…
As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their susceptibility to adversarial perturbations has emerged as a…
Deep learning models, which are increasingly being used in the field of medical image analysis, come with a major security risk, namely, their vulnerability to adversarial examples. Adversarial examples are carefully crafted samples that…
Adversarial Training (AT) is known as an effective approach to enhance the robustness of deep neural networks. Recently researchers notice that robust models with AT have good generative ability and can synthesize realistic images, while…
Machine learning models, especially deep neural networks (DNNs), have been shown to be vulnerable against adversarial examples which are carefully crafted samples with a small magnitude of the perturbation. Such adversarial perturbations…
Most current methods generate adversarial examples with the $L_p$ norm specification. As a result, many defense methods utilize this property to eliminate the impact of such attacking algorithms. In this paper,we instead introduce…
In recent years, the rapid development of generative artificial intelligence technology has significantly lowered the barrier to creating high-quality fake images, posing a serious challenge to information authenticity and credibility.…
Unsupervised semantic segmentation (USS) aims to achieve high-quality segmentation without manual pixel-level annotations. Existing USS models provide coarse category classification for regions, but the results often have blurry and…
Self-supervised pre-training has drawn increasing attention in recent years due to its superior performance on numerous downstream tasks after fine-tuning. However, it is well-known that deep learning models lack the robustness to…
Segment Anything Model (SAM) has recently shown its powerful effectiveness in visual segmentation tasks. However, there is less exploration concerning how SAM works on audio-visual tasks, such as visual sound localization and segmentation.…
Image generation remains a fundamental problem in artificial intelligence in general and deep learning in specific. The generative adversarial network (GAN) was successful in generating high quality samples of natural images. We propose a…
Palmprint recognition is deployed in security-critical applications, including access control and palm-based payment, due to its contactless acquisition and highly discriminative ridge-and-crease textures. However, the robustness of deep…
The Segment Anything Model (SAM) has demonstrated strong performance in image segmentation of natural scene images. However, its effectiveness diminishes markedly when applied to specific scientific domains, such as Scanning Probe…
Deep learning-based time series models are being extensively utilized in engineering and manufacturing industries for process control and optimization, asset monitoring, diagnostic and predictive maintenance. These models have shown great…