arXiv research

Adversarial consistency depends on the uniqueness of adversarial Bayes classifiers.

Study on calibration and consistency of adversarial surrogate losses.

Paper bounds convergence rate of adversarial surrogate risk.

This paper improves adversarial robustness of deep learning models.

New algorithms for regression with adversarial responses on various metric spaces.

Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial methods in more challenging language pairs. In this work, we revisit adversarial autoe…

New findings on universal learning in contextual bandits with adversarial rewards.

Study reveals how high-dimensional models are vulnerable to consistent adversarial attacks.

This research analyzes the consistency of convex and nonconvex surrogate losses for adversarially robust classification.

Study improves $H$-consistency bounds for regression analysis.

This study examines when non-parametric methods are robust to adversarial examples.

SARD improves adversarial robustness in two-stage L2D systems.

Study on $H$-consistency bounds for machine learning surrogates.

Study on learning strategies in adaptive Markov games with policy regret as metric.

We improve adversarial robustness calibration analysis for broader hypothesis sets.

Sometimes it is not enough for a DNN to produce an outcome. For example, in applications such as healthcare, users need to understand the rationale of the decisions. Therefore, it is imperative to develop algorithms to learn models with good interpretability (Doshi-Velez 2017). An important factor that leads to the lac…

Theoretical analysis of cross-entropy loss functions and their robustness.

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) m…

New algorithm explains DNN predictions using adversarial attacks.

Current multi-reference style transfer models for Text-to-Speech (TTS) perform sub-optimally on disjoints datasets, where one dataset contains only a single style class for one of the style dimensions. These models generally fail to produce style transfer for the dimension that is underrepresented in the dataset. In th…

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained model. This backdoor can then be activated during inference by a backdoor trigger…

This paper investigates the theory of robustness against adversarial attacks. It focuses on the family of randomization techniques that consist in injecting noise in the network at inference time. These techniques have proven effective in many contexts, but lack theoretical arguments. We close this gap by presenting a …

Bayes-optimal classifiers are robust to adversarial attacks, unlike CNNs trained on the same data.

CycleGAN (Zhu et al. 2017) is one recent successful approach to learn a transformation between two image distributions. In a series of experiments, we demonstrate an intriguing property of the model: CycleGAN learns to "hide" information about a source image into the images it generates in a nearly imperceptible, high-…

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

In this paper, we investigate algorithms for anomaly detection. Previous anomaly detection methods focus on modeling the distribution of non-anomalous data provided during training. However, this does not necessarily ensure the correct detection of anomalous data. We propose a new Regularized Cycle Consistent Generativ…

Improves GAN-based semi-supervised learning with consistency regularization.

Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can make the well-trained models output wrong labels with high confidence. In this pap…

New SSIM measure improves adversarial attacks' perceptual quality.

Adversarial attacks on probabilistic state-space models affect latent state and policy decisions.

The paper studies the asymptotic behavior of adversarial training under $\ell_\infty$-perturbation.

Although voice conversion (VC) algorithms have achieved remarkable success along with the development of machine learning, superior performance is still difficult to achieve when using nonparallel data. In this paper, we propose using a cycle-consistent adversarial network (CycleGAN) for nonparallel data-based VC train…

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

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…

Generative adversarial network for probabilistic forecasting of random systems.

CNN-F uses generative feedback to improve neural networks' robustness to perturbations.

We study the Thompson sampling algorithm in an adversarial setting, specifically, for adversarial bit prediction. We characterize the bit sequences with the smallest and largest expected regret. Among sequences of length $T$ with $k < \frac{T}{2}$ zeros, the sequences of largest regret consist of alternating zeros and …

Given a pair of graphs $G_1$ and $G_2$ and a vertex set of interest in $G_1$, the vertex nomination (VN) problem seeks to find the corresponding vertices of interest in $G_2$ (if they exist) and produce a rank list of the vertices in $G_2$, with the corresponding vertices of interest in $G_2$ concentrating, ideally, at…

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 …

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…

Adversarial policies beat superhuman Go AI systems.

Deep neural networks have been widely deployed in various machine learning tasks. However, recent works have demonstrated that they are vulnerable to adversarial examples: carefully crafted small perturbations to cause misclassification by the network. In this work, we propose a novel defense mechanism called Boundary …

DART tackles adversarial robustness in domain adaptation without labeled target data.

We propose a parallel-data-free voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is general purpose, high quality, and parallel-data free and works without any extra data, modules, or alignment procedure. It also avoids over-smoothi…

Improved inter-scanner MS lesion segmentation through adversarial training.

Adaptive networks improve model robustness through conditional normalization.

Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found. We turn our attention to the field of Autonomous navigation wherein adverse weather conditions such as fog have a drastic effect on the pred…

Paper improves adversarial training using a learned optimizer.