arXiv research

This paper investigates how network width and depth affect adversarially robust DNNs.

Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel approach for learning robust classifier. Our main idea is: adversarial examples for…

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 perturbation that can easily fool the classifier network by using a gradient of each imag…

Study analyzes adversarial training dynamics without data distribution assumptions.

In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures. To address this problem and improve the robustness …

Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and deploying this method - expensive in terms of extra memory and computation costs; …

BPN defends against adversarial attacks by generating beneficial perturbations.

NTK neural networks are robust to adversarial attacks in nonparametric regression.

Adaptive networks improve model robustness through conditional normalization.

This work simplifies adversarial attacks using neural networks, reducing computation and improving training convergence.

The paper examines how neural network topology affects adversarial robustness.

New method improves neural network interpretability against adversarial attacks.

Adversarial attacks add perturbations to the input features with the intent of changing the classification produced by a machine learning system. Small perturbations can yield adversarial examples which are misclassified despite being virtually indistinguishable from the unperturbed input. Classifiers trained with stan…

Adversarial training achieves optimal test error for shallow networks.

New method makes neural networks more resilient to location-optimized adversarial patches.

New defense method reduces adversarial attacks on neural networks.

In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the unperturbed input, and yet are misclassified. In standard neural networks used for deep learning, atta…

Adversarial robustness improved by sparsity in network weights.

Proposes BATer for improved adversarial example detection.

Deep neural networks with adversarial training achieve sup-norm convergence for nonparametric regression.

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples. Adversarial examples are imperceptible to …

Adversarial attacks during the testing phase of neural networks pose a challenge for the deployment of neural networks in security critical settings. These attacks can be performed by adding noise that is imperceptible to humans on top of the original data. By doing so, an attacker can create an adversarial sample, whi…

This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks. Recent work suggests that these architectures are more robust towards adversarial attacks than other neural networks. However, our experiments show that capsule networks can be fooled as easily as convolutional neur…

Two-layer networks trained on low-dimensional subspaces are vulnerable to adversarial examples.

Colored noise improves neural network robustness against adversarial attacks.

Bayesian neural networks are vulnerable to adversarial attacks.

Detects adversarial inputs in deep learning models without modifying the main network.

Adversarial noises are linearly separable for random neural networks.

Random deep neural networks are robust to adversarial examples, scaling with input size and dimension.

New method creates powerful, transferable adversarial attacks for deep learning networks.

Random convolutional networks can be fooled with adversarial examples.

New measure assesses deep neural networks' robustness to adversarial attacks.

Proposes using mode connectivity to improve adversarial robustness of neural networks.

Lazy neural networks are vulnerable to adversarial attacks.

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient updates should be statistically indistinguishable from each other. We enforce this c…

Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new clas…

It is becoming increasingly clear that many machine learning classifiers are vulnerable to adversarial examples. In attempting to explain the origin of adversarial examples, previous studies have typically focused on the fact that neural networks operate on high dimensional data, they overfit, or they are too linear. H…

Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this problem is to retrain the networks using those adversarial examples, namely adversa…

CAT improves robustness of neural networks by customizing perturbation levels.

Study finds discrepancies in model explanations for clean vs. adversarial inputs.

Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.

Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of SER systems by showing the susceptibility of deep neural networks to adversarial …

Wide networks learn from adversarial perturbations effectively.

Study evaluates adversarial training for deep learning IDSs against various attacks.

Study shows prior Lipschitz continuity can improve adversarial robustness of Bayesian Neural Networks.

A recent paper by Liu et al. combines the topics of adversarial training and Bayesian Neural Networks (BNN) and suggests that adversarially trained BNNs are more robust against adversarial attacks than their non-Bayesian counterparts. Here, I analyze the proposed defense and suggest that one needs to adjust the adversa…

Recent studies on the adversarial vulnerability of neural networks have shown that models trained with the objective of minimizing an upper bound on the worst-case loss over all possible adversarial perturbations improve robustness against adversarial attacks. Beside exploiting adversarial training framework, we show t…

Study reveals how neural network biases align with adversarial attack frequencies.