相关论文: PASA: Attack Agnostic Unsupervised Adversarial Det…

Transferability of adversarial examples is of central importance for attacking an unknown model, which facilitates adversarial attacks in more practical scenarios, e.g., black-box attacks. Existing transferable attacks tend to craft…

Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can…

Deep neural networks (DNNs) can be easily fooled by adversarial attacks during inference phase when attackers add imperceptible perturbations to original examples, i.e., adversarial examples. Many works focus on adversarial detection and…

Security-sensitive applications that rely on Deep Neural Networks (DNNs) are vulnerable to small perturbations that are crafted to generate Adversarial Examples(AEs). The AEs are imperceptible to humans and cause DNN to misclassify them.…

This paper introduces stochastic sparse adversarial attacks (SSAA), standing as simple, fast and purely noise-based targeted and untargeted attacks of neural network classifiers (NNC). SSAA offer new examples of sparse (or $L_0$) attacks…

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…

We propose a new adversarial attack to Deep Neural Networks for image classification. Different from most existing attacks that directly perturb input pixels, our attack focuses on perturbing abstract features, more specifically, features…

Many machine learning classifiers are vulnerable to adversarial perturbations. An adversarial perturbation modifies an input to change a classifier's prediction without causing the input to seem substantially different to human perception.…

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

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…

Adversarial learning is a widely used technique in fair representation learning to remove the biases on sensitive attributes from data representations. It usually requires to incorporate the sensitive attribute labels as prediction targets.…

Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful implementation of these models however, usually relies on…

Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and spatial information.…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

We present a method for adversarial attack detection based on the inspection of a sparse set of neurons. We follow the hypothesis that adversarial attacks introduce imperceptible perturbations in the input and that these perturbations…

Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…

Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…

Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised learning) as the…