Related papers: A randomized gradient-free attack on ReLU networks
Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…
Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can…
Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…
This paper introduces adversarial attacks targeting a Graph Neural Network (GNN) based radio resource management system in point to point (P2P) communications. Our focus lies on perturbing the trained GNN model during the test phase,…
The emergence of deep learning led to the broad usage of neural networks in the time series domain for various applications, including finance and medicine. While powerful, these models are prone to adversarial attacks: a benign targeted…
Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we…
Adversarial training provides a principled approach for training robust neural networks. From an optimization perspective, adversarial training is essentially solving a bilevel optimization problem. The leader problem is trying to learn a…
Adversarial examples are carefully constructed modifications to an input that completely change the output of a classifier but are imperceptible to humans. Despite these successful attacks for continuous data (such as image and audio…
Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…
The incredible effectiveness of adversarial attacks on fooling deep neural networks poses a tremendous hurdle in the widespread adoption of deep learning in safety and security-critical domains. While adversarial defense mechanisms have…
Deep neural networks are known to be vulnerable to adversarial attacks (AA). For an image recognition task, this means that a small perturbation of the original can result in the image being misclassified. Design of such attacks as well as…
Though deep neural network has hit a huge success in recent studies and applica- tions, it still remains vulnerable to adversarial perturbations which are imperceptible to humans. To address this problem, we propose a novel network called…
In the last decade, deep neural networks have proven to be very powerful in computer vision tasks, starting a revolution in the computer vision and machine learning fields. However, deep neural networks, usually, are not robust to…
A significant threat to the recent, wide deployment of machine learning-based systems, including deep neural networks (DNNs), is adversarial learning attacks. We analyze possible test-time evasion-attack mechanisms and show that, in some…
Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples. In this paper, we propose a gradient-based adversarial attack against…
Deep learning (DL) is becoming popular as a new tool for many applications in wireless communication systems. However, for many classification tasks (e.g., modulation classification) it has been shown that DL-based wireless systems are…
Adversarial attacks against deep neural networks (DNNs) are continuously evolving, requiring increasingly powerful defense strategies. We develop a novel adversarial defense framework inspired by the adaptive immune system: the Robust…
One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…
We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial…