arXiv research

Adversarial consistency depends on the uniqueness of adversarial Bayes classifiers.

Robust RL with learned optimal adversary improves agent performance under adversarial state observations.

I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, includi…

Paper tackles robustness in adversarial noise with a meta-optimizer.

New method simplifies and improves imitation learning without adversarial techniques.

The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threat to a range of mission-critical deep learning systems and applications. This paper ta…

This paper improves adversarial robustness of deep learning models.

Bayesian adversaries can outsmart traditional adversarial attacks.

Study on robustness in linear regression models, focusing on adversarial perturbations.

We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We…

New framework for understanding adversarial and stochastic learning.

This paper discusses adversarial attacks on cyber security systems using machine learning.

Paper proposes a method to train robust neural networks without labeled data.

BN helps learn fragile features, which can improve adversarial robustness.

Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which leverages clean and adversarial samples to optimize the initialization of a lear…

A Bayesian framework models adversarial uncertainty for robust machine learning.

New approach optimizes policies in adversarial MDPs using adversarial learning.

Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial examples. The goal of our work is to produce networks which both perform well a…

This paper studies adversarial examples in NIDS, revealing their vulnerability.

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…

New method improves graph representations against adversarial attacks.

Federated learning can be vulnerable to adversarial attacks, which this work addresses.

Adversarial Robustness Toolbox (ART) is a Python library supporting developers and researchers in defending Machine Learning models (Deep Neural Networks, Gradient Boosted Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, Gaussian Processes, Decision Trees, Scikit-learn Pipelines, etc.) agai…

Generative Adversarial Networks (GAN) have shown promising results on a wide variety of complex tasks. Recent experiments show adversarial training provides useful gradients to the generator that helps attain better performance. In this paper, we intend to theoretically analyze whether supervised learning with adversar…

Study compares adversarial regularization to sole supervision in machine learning.

ACL improves robustness with unlabeled data, and we analyze its generalization using Rademacher complexity.

Machine learning-based IDSs in ICS are vulnerable to adversarial attacks that can bypass them.

Paper improves adversarial training using a learned optimizer.

Survey of graph adversarial learning tasks and their attacks and defenses.

Study adversarial perturbations in classification, analyzing learning and certification.

Dynamic defense against Byzantine poisoning in federated learning.

This paper examines how adversarial perturbations affect model performance and equilibrium learning.

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 robust classifier, while the follower problem is trying to generate adversarial s…

Wide networks learn from adversarial perturbations effectively.

Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust models. In order to scale adversarial training for large datasets, these perturbati…

Analyzes adversarial training's impact on loss landscape, proposing PAS to improve model performance.

MAT combines meta-learning and adversarial training to defend against universal patches.

By injecting adversarial examples into training data, adversarial training is promising for improving the robustness of deep learning models. However, most existing adversarial training approaches are based on a specific type of adversarial attack. It may not provide sufficiently representative samples from the adversa…

Adversaries with multiple antennas can fool deep learning modulators more effectively.

The paper evaluates machine learning cyber defenses using log data against adversarial attacks.

New algorithms achieve no-regret learning even with adversarial transitions and losses.

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global …

Unified ML and adversarial learning via α-divergence.

DeepRobust is a PyTorch library for adversarial attacks and defenses.

Interpreting machine learning models helps understand adversarial attacks and defenses.

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we show adversarial attacks are also effective when targeting neural …

This paper explores the connection between adversarial and knowledge transferability.

Study explores bias-variance in adversarial machine learning.