Related papers: Using Anomaly Feature Vectors for Detecting, Class…
We investigate the problem of identifying adversarial attacks on image-based neural networks. We present intriguing experimental results showing significant discrepancies between the explanations generated for the predictions of a model on…
Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding…
Anomaly detection is a difficult problem in many areas and has recently been subject to a lot of attention. Classifying unseen data as anomalous is a challenging matter. Latest proposed methods rely on Generative Adversarial Networks (GANs)…
Deep Neural Networks (DNNs) have recently made significant progress in many fields. However, studies have shown that DNNs are vulnerable to adversarial examples, where imperceptible perturbations can greatly mislead DNNs even if the full…
Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the…
Despite high accuracy of Convolutional Neural Networks (CNNs), they are vulnerable to adversarial and out-distribution examples. There are many proposed methods that tend to detect or make CNNs robust against these fooling examples.…
Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such…
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbations can completely change the classification results. Their vulnerability has led to a surge of research in this direction. However, most…
Optical character recognition (OCR) is widely applied in real applications serving as a key preprocessing tool. The adoption of deep neural network (DNN) in OCR results in the vulnerability against adversarial examples which are crafted to…
Recently, the problem of robustness of pre-trained language models (PrLMs) has received increasing research interest. Latest studies on adversarial attacks achieve high attack success rates against PrLMs, claiming that PrLMs are not robust.…
Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally…
Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class…
Visual anomaly detection targets to detect images that notably differ from normal pattern, and it has found extensive application in identifying defective parts within the manufacturing industry. These anomaly detection paradigms…
Neural networks are vulnerable to a wide range of erroneous inputs such as adversarial, corrupted, out-of-distribution, and misclassified examples. In this work, we train a linear SVM classifier to detect these four types of erroneous data…
The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same…
Susceptibility of deep neural networks to adversarial attacks poses a major theoretical and practical challenge. All efforts to harden classifiers against such attacks have seen limited success. Two distinct categories of samples to which…
Guaranteeing the security of transactional systems is a crucial priority of all institutions that process transactions, in order to protect their businesses against cyberattacks and fraudulent attempts. Adversarial attacks are novel…
Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown deep diagnostic models may not be robust in the inference…
Deep Neural Networks (DNNs) are vulnerable to adversarial examples, while adversarial attack models, e.g., DeepFool, are on the rise and outrunning adversarial example detection techniques. This paper presents a new adversarial example…
We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by the classifier…