相关论文: Defending Adversarial Attacks via Semantic Feature…

Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks. While existing adversarial perturbations are primarily applied to uncompressed images or compressed images…

Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defend against…

Adversarially perturbed images of text can cause sophisticated OCR systems to produce misleading or incorrect transcriptions from seemingly invisible changes to humans. Some of these perturbations even survive physical capture, posing…

Recent studies reveal that Convolutional Neural Networks (CNNs) are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. Many adversarial defense methods improve robustness at the cost of…

Adversarial examples are inputs to a machine learning system that result in an incorrect output from that system. Attacks launched through this type of input can cause severe consequences: for example, in the field of image recognition, a…

Deep learning based methods for medical images can be easily compromised by adversarial examples (AEs), posing a great security flaw in clinical decision-making. It has been discovered that conventional adversarial attacks like PGD which…

Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted…

Deep learning models for image classification have become standard tools in recent years. A well known vulnerability of these models is their susceptibility to adversarial examples. These are generated by slightly altering an image of a…

A common observation regarding adversarial attacks is that they mostly give rise to false activation at the penultimate layer to fool the classifier. Assuming that these activation values correspond to certain features of the input, the…

Deep neural networks are capable of state-of-the-art performance in many classification tasks. However, they are known to be vulnerable to adversarial attacks -- small perturbations to the input that lead to a change in classification. We…

Despite the great progress of neural network-based (NN-based) machinery fault diagnosis methods, their robustness has been largely neglected, for they can be easily fooled through adding imperceptible perturbation to the input. For fault…

Facial attributes, emerging soft biometrics, must be automatically and reliably extracted from images in order to be usable in stand-alone systems. While recent methods extract facial attributes using deep neural networks (DNNs) trained on…

Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filtering out adversarial…

Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered…

Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we…

Deep learning algorithms have been shown to be powerful in many communication network design problems, including that in automatic modulation classification. However, they are vulnerable to carefully crafted attacks called adversarial…

Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks…

In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…

Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…