Related papers: Towards Adversarial Robustness and Uncertainty Qua…
Recent advances in multimodal foundation models have set new standards in few-shot anomaly detection. This paper explores whether high-quality visual features alone are sufficient to rival existing state-of-the-art vision-language models.…
While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…
The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…
Although deep neural networks have shown promising performances on various tasks, even achieving human-level performance on some, they are shown to be susceptible to incorrect predictions even with imperceptibly small perturbations to an…
Rapid progress is being made in developing large, pretrained, task-agnostic foundational vision models such as CLIP, ALIGN, DINOv2, etc. In fact, we are approaching the point where these models do not have to be finetuned downstream, and…
Unsupervised anomaly detection (AD) in medical images aims to identify abnormal regions without relying on pixel-level annotations, which is crucial for scalable and label-efficient diagnostic systems. In this paper, we propose a novel…
Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in…
Few-shot anomaly detection streamlines and simplifies industrial safety inspection. However, limited samples make accurate differentiation between normal and abnormal features challenging, and even more so under category-agnostic…
Anomaly detection methods typically require extensive normal samples from the target class for training, limiting their applicability in scenarios that require rapid adaptation, such as cold start. Zero-shot and few-shot anomaly detection…
In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…
Time series anomaly detection is extensively studied in statistics, economics, and computer science. Over the years, numerous methods have been proposed for time series anomaly detection using deep learning-based methods. Many of these…
Despite their unprecedented performance in various domains, utilization of Deep Neural Networks (DNNs) in safety-critical environments is severely limited in the presence of even small adversarial perturbations. The present work develops a…
Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and…
Zero-shot anomaly detection aims to identify defects in unseen categories without target-specific training. Existing methods usually apply the same feature transformation to all samples, treating normal and anomalous data uniformly despite…
Deep Neural Networks (DNNs) are known to be susceptible to adversarial examples. Adversarial examples are maliciously crafted inputs that are designed to fool a model, but appear normal to human beings. Recent work has shown that pixel…
Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these…
Deep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial…
DINO models provide rich patch-level representations that have recently enabled strong performance in unsupervised anomaly detection (UAD). Most existing methods extract patch embeddings from ``normal'' images and model them independently,…
As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities. Designed and trained from certain statistical distributions of data, AI's deep neural networks (DNNs) remain…
With increased reliance on Internet based technologies, cyberattacks compromising users' sensitive data are becoming more prevalent. The scale and frequency of these attacks are escalating rapidly, affecting systems and devices connected to…