Related papers: Adversarially Robust Dense-Sparse Tradeoffs via He…
Transfer learning, in which a network is trained on one task and re-purposed on another, is often used to produce neural network classifiers when data is scarce or full-scale training is too costly. When the goal is to produce a model that…
Recent work revealed a tight connection between adversarial robustness and restricted forms of symbolic explanations, namely distance-based (formal) explanations. This connection is significant because it represents a first step towards…
Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…
Adversarial training is widely used to make classifiers robust to a specific threat or adversary, such as $\ell_p$-norm bounded perturbations of a given $p$-norm. However, existing methods for training classifiers robust to multiple threats…
Deep neural networks (DNNs) are found to be vulnerable to adversarial noise. They are typically misled by adversarial samples to make wrong predictions. To alleviate this negative effect, in this paper, we investigate the dependence between…
Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…
Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performance, prior work has…
Group distributionally robust optimization, which aims to improve robust accuracies -- worst-group and unbiased accuracies -- is a prominent algorithm used to mitigate spurious correlations and address dataset bias. Although existing…
This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial training (AT) improves robustness, it degrades the standard…
Mixup is a procedure for data augmentation that trains networks to make smoothly interpolated predictions between datapoints. Adversarial training is a strong form of data augmentation that optimizes for worst-case predictions in a compact…
Although the recent progress is substantial, deep learning methods can be vulnerable to the maliciously generated adversarial examples. In this paper, we present a novel training procedure and a thresholding test strategy, towards robust…
The Hybrid Online Learning Problem, where features are drawn i.i.d. from an unknown distribution but labels are generated adversarially, is a well-motivated setting positioned between statistical and fully-adversarial online learning. Prior…
We present an effective way to predict search query-item relationship. We combine pre-trained transformer and LSTM models, and increase model robustness using adversarial training, exponential moving average, multi-sampled dropout, and…
Dataset distillation synthesizes compact datasets that enable models to achieve performance comparable to training on the original large-scale datasets. However, existing distillation methods overlook the robustness of the model, resulting…
Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. However, most existing AT methods adopt a specific attack to craft adversarial examples,…
This paper introduces a comprehensive framework designed to analyze and secure decision-support systems trained with Deep Reinforcement Learning (DRL), prior to deployment, by providing insights into learned behavior patterns and…
As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study several key questions…
We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…
Existing high-dimensional online learning methods often face the challenge that their error bounds, or per-batch sample sizes, diverge as the number of data batches increases. To address this issue, we propose an asynchronous decomposition…
Adversarial robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time. In the context of image tasks, many algorithms have been proposed to make neural networks robust to…