arXiv research

AWP improves robustness by flattening weight loss landscape.

Adversarial training makes logistic regression weight loss landscapes sharper.

Adversarial robustness improved by sparsity in network weights.

Adversarial weight perturbations can inject backdoors into trained neural models.

FAIR method uses adversarial training to learn fair instance weights.

T-BFA targets and misleads specific DNN inputs to a chosen output.

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…

Proposes SWA for adversarial training to improve model robustness.

A new method improves adversarial robustness by optimizing importance weights.

Characterizes deep neural network weight space for adversarial attacks.

The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective. Here, we derive importance weighted extensions to AVB and AAE. These latent variable models use implicitly defined inference networks whose approx…

CWAN tackles multi-source heterogeneous domain adaptation with conditional weighting.

LGV boosts adversarial attacks by improving surrogate models.

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…

Algorithm learns expert weights to minimize regret in adversarial setting.

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…

New approach optimizes policies in adversarial MDPs using adversarial learning.

Adversarial weighting improves regression task adaptation.

This paper examines weight initialization for 1-Lipschitz networks to improve robustness against adversarial attacks.

Most random ReLU networks are vulnerable to small, Euclidean adversarial perturbations.

There is a growing body of literature showing that deep neural networks are vulnerable to adversarial input modification. Recently this work has been extended from image classification to malware classification over boolean features. In this paper we present several new methods for training restricted networks in this …

Performance-critical machine learning models should be robust to input perturbations not seen during training. Adversarial training is a method for improving a model's robustness to some perturbations by including them in the training process, but this tends to exacerbate other vulnerabilities of the model. The adversa…

Proposes a new method to improve regression models with reweighted samples.

The susceptibility of deep learning to adversarial attack can be understood in the framework of the Renormalisation Group (RG) and the vulnerability of a specific network may be diagnosed provided the weights in each layer are known. An adversary with access to the inputs and outputs could train a second network to clo…

Paper tackles ranking items with a semi-random comparison graph and a monotone adversary.

Convolutional neural networks (CNNs) are known for their good performance and generalization in vision-related tasks and have become state-of-the-art in both application and research-based domains. However, just like other neural network models, they suffer from a susceptibility to noise and adversarial attacks. An adv…

Adversarial training effectiveness varies widely due to inconsistent training settings.

New research shows flat minima in robust loss landscapes correlate with good adversarial robustness.

Many machine learning models are vulnerable to adversarial attacks; for example, adding adversarial perturbations that are imperceptible to humans can often make machine learning models produce wrong predictions with high confidence. Moreover, although we may obtain robust models on the training dataset via adversarial…

Adversarial training purifies hidden weights to remove small perturbations.

Many state-of-the-art machine learning models such as deep neural networks have recently shown to be vulnerable to adversarial perturbations, especially in classification tasks. Motivated by adversarial machine learning, in this paper we investigate the robustness of sparse regression models with strongly correlated co…

The paper proposes effective margin regularization to improve adversarial robustness in deep neural networks.

Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of demonstrations, it faces several practical challenges such as potential training i…

We propose regularizing the empirical loss for semi-supervised learning by acting on both the input (data) space, and the weight (parameter) space. We show that the two are not equivalent, and in fact are complementary, one affecting the minimality of the resulting representation, the other insensitivity to nuisance va…

Study examines uncertainty in adversarially trained models and proposes improved AT methods.

Paper improves robustness of GNNs against adversarial attacks.

Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under $\ell_\infty$ attacks. To combat this problem, techniques like adversarial training have been employed to obtain models which are robust on the training set. However, the …

Adversarial CBO optimizes under interventions by adversaries and non-stationarities.

New method enhances adversarial robustness of deep learning models.

New algorithm reduces regret in RL with adversarial corruption.

Generative Adversarial Network model for class-imbalanced tabular data.

Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in automatic speech recognition (ASR). In ADIT, an auxiliary domain classifier takes in equally-weighted deep features from a deep neural network …

The use of unsupervised data in addition to supervised data in training discriminative neural networks has improved the performance of this clas- sification scheme. However, the best results were achieved with a training process that is divided in two parts: first an unsupervised pre-training step is done for initializ…

Graph-based framework for provably robust adversarial training.

Study analyzes adversarial training dynamics without data distribution assumptions.

Colored noise improves neural network robustness against adversarial attacks.

Stablecoin system improves resilience to extreme market events.

The worst-case training principle that minimizes the maximal adversarial loss, also known as adversarial training (AT), has shown to be a state-of-the-art approach for enhancing adversarial robustness. Nevertheless, min-max optimization beyond the purpose of AT has not been rigorously explored in the adversarial contex…