arXiv research

Proposes an adversarial process using cosine similarity to improve robustness of models.

Guarantees robustness of Gaussian process classifiers against adversarial attacks.

Detects and corrects adversarial images using image processing.

Bayesian adversaries can outsmart traditional adversarial attacks.

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial training is the process of explicitly training a model on adversarial examples,…

Adversarial deep hedging learns to hedge without specifying asset price models.

We propose a novel adversarial learning strategy for mixture models of Hawkes processes, leveraging data augmentation techniques of Hawkes process in the framework of self-paced learning. Instead of learning a mixture model directly from a set of event sequences drawn from different Hawkes processes, the proposed metho…

Deep learning algorithms and networks are vulnerable to perturbed inputs which is known as the adversarial attack. Many defense methodologies have been investigated to defend against such adversarial attack. In this work, we propose a novel methodology to defend the existing powerful attack model. We for the first time…

This paper studies adversarial attacks on Gaussian process bandits.

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

NP-Attack reduces query counts for black-box adversarial attacks.

Improved FPL algorithms for adversarial MDPs with better regret bounds.

Detects audio adversarial examples using anomalous pattern detection.

Paper proposes a GAN-based method for better next event prediction in business processes.

RTFE provides adversarial robustness to multiple models.

Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN), are primarily derived from empirical developments, and their security guarantee…

This paper introduces blind adversarial pruning to balance accuracy, efficiency, and robustness in neural networks.

Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the image processing field to the input word embedding space instead of the discrete…

Overparameterized linear model shows strong classification but weak regression, susceptible to adversarial perturbations.

Differentiable adversarial attacks improve model robustness in MTPP models.

The paper analyzes adversarial robustness of Gaussian processes.

Charmer improves character-level adversarial attacks for language models.

A two-layer network corrects logits to defend adversarial attacks.

KSGAN uses KS distance for deep generative modeling.

Recent breakthroughs in the field of deep learning have led to advancements in a broad spectrum of tasks in computer vision, audio processing, natural language processing and other areas. In most instances where these tasks are deployed in real-world scenarios, the models used in them have been shown to be susceptible …

The NIPS 2018 Adversarial Vision Challenge is a competition to facilitate measurable progress towards robust machine vision models and more generally applicable adversarial attacks. This document is an updated version of our competition proposal that was accepted in the competition track of 32nd Conference on Neural In…

CGAN fails to improve deterministic sequence predictions, revealing a theoretical limitation.

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…

In several reinforcement learning (RL) scenarios, mainly in security settings, there may be adversaries trying to interfere with the reward generating process. In this paper, we introduce Threatened Markov Decision Processes (TMDPs), which provide a framework to support a decision maker against a potential adversary in…

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

Generative adversarial networks fix aliasing issues by making signals continuous.

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

Proposes a probabilistic method for generating semantically-aware adversarial examples.

We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_2$ norm on CIFAR-10. We obtain verifiable average case and worst case robustness guarantees, based on the expected and maximum values of the…

Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversar…

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

WDAIL uses Wasserstein distance for more effective reward shaping in IL.

Deep neural networks (DNNs) have recently achieved state-of-the-art performance and provide significant progress in many machine learning tasks, such as image classification, speech processing, natural language processing, etc. However, recent studies have shown that DNNs are vulnerable to adversarial attacks. For inst…

Improves classifier performance in multi-stage processes with adversarial autoencoders and multi-task learning.

Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to the input images are sufficient to fool the most powerful deep neural networks. Va…

New approach optimizes policies in adversarial MDPs using adversarial learning.

An adversarial detector identifies anomalous sequences in sequential data.

DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.

New framework for RL with opponents, improving learning outcomes.

We propose a method to generate audio adversarial examples that can attack a state-of-the-art speech recognition model in the physical world. Previous work assumes that generated adversarial examples are directly fed to the recognition model, and is not able to perform such a physical attack because of reverberation an…

New method tackles adversarial sign-corrupted isotonic regression, estimating monotonic signals under heavy dependence.

Analyzes biased random walks and corrupted intervals in adversarial settings.

We study the problem of multimodal generative modelling of images based on generative adversarial networks (GANs). Despite the success of existing methods, they often ignore the underlying structure of vision data or its multimodal generation characteristics. To address this problem, we introduce the Dirichlet prior fo…