arXiv research

This paper analyzes the limits of neural networks under adversarial attacks.

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

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

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 …

New attack method improves neural network security.

New defense method reduces adversarial attacks on neural networks.

Lazy neural networks are vulnerable to adversarial attacks.

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

Proposes BATer for improved adversarial example detection.

The paper examines how neural network topology affects adversarial robustness.

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

Adversarial training adds dynamic perturbations to neural networks for robustness.

Validates neural networks inputs to protect against adversarial examples.

New metric detects adversarial samples with high accuracy.

Adversarial noises are linearly separable for random neural networks.

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

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…

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

Colored noise improves neural network robustness against adversarial attacks.

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 …

New method improves DNN robustness against adversarial attacks.

Bayesian neural networks are vulnerable to adversarial attacks.

DeepMPM uses MPM to make deep neural networks more robust against adversarial attacks.

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…

It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process. The gap between robust deep learning systems in real world applications and vulnerable neural networks is still large. Current adversarial training strategies improve the robustness ag…

SGD-trained neural networks generalize well even with adversarial label noise.

Bayesian explanations are more resilient to adversarial attacks than deterministic ones.

New method improves neural network interpretability against adversarial attacks.

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

Deep Neural Networks are built to generalize outside of training set in mind by using techniques such as regularization, early stopping and dropout. But considerations to make them more resilient to adversarial examples are rarely taken. As deep neural networks become more prevalent in mission-critical and real-time sy…

In recent years, it has been found that neural networks can be easily fooled by adversarial examples, which is a potential safety hazard in some safety-critical applications. Many researchers have proposed various method to make neural networks more robust to white-box adversarial attacks, but an effective method have …

CAT improves robustness of neural networks by customizing perturbation levels.

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

Sparse neural networks can be robust to adversarial attacks.

Characterizes deep neural network weight space for adversarial attacks.

Recently, Neural networks have seen a huge surge in its adoption due to their ability to provide high accuracy on various tasks. On the other hand, the existence of adversarial examples have raised suspicions regarding the generalization capabilities of neural networks. In this work, we focus on the weight matrix learn…

Enhances neural network robustness with Mixup and TLAT.

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

The paper identifies potential adversarial samples near decision boundaries of neural networks.

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

Recently, there has been an abundance of works on designing Deep Neural Networks (DNNs) that are robust to adversarial examples. In particular, a central question is which features of DNNs influence adversarial robustness and, therefore, can be to used to design robust DNNs. In this work, this problem is studied throug…

Paper provides robustness bounds for GNNs against adversarial attacks.

Minimax defense improves neural network security against gradient-based attacks.

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

Neural networks trained with backpropagation, the standard algorithm of deep learning which uses weight transport, are easily fooled by existing gradient-based adversarial attacks. This class of attacks are based on certain small perturbations of the inputs to make networks misclassify them. We show that less biologica…

Study reveals how neural network smoothness affects their vulnerability to adversarial attacks.

Single gradient step finds adversarial examples in random neural networks.

The paper tackles adversarial attacks on recurrent neural networks.