相关论文: Explaining Classifiers using Adversarial Perturbat…

Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in providing…

There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs) in machine vision; most of these perturbation-based attacks target object classifiers. Inspired by the observation that humans…

The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence. Limited by the extreme difficulty in…

Explaining decisions of black-box classifiers is paramount in sensitive domains such as medical imaging since clinicians confidence is necessary for adoption. Various explanation approaches have been proposed, among which perturbation based…

Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic…

We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and the semantics of the labels. The proposed framework combines a structure loss and a semantic adversarial loss in a…

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…

We cannot guarantee that training datasets are representative of the distribution of inputs that will be encountered during deployment. So we must have confidence that our models do not over-rely on this assumption. To this end, we…

Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations…

This paper aims to explain adversarial attacks in terms of how adversarial perturbations contribute to the attacking task. We estimate attributions of different image regions to the decrease of the attacking cost based on the Shapley value.…

Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we…

Adversarial robust models have been shown to learn more robust and interpretable features than standard trained models. As shown in [\cite{tsipras2018robustness}], such robust models inherit useful interpretable properties where the…

Intelligent systems possess a crucial characteristic of breaking complicated problems into smaller reusable components or parts and adjusting to new tasks using these part representations. However, current part-learners encounter…

Deep visual models are susceptible to adversarial perturbations to inputs. Although these signals are carefully crafted, they still appear noise-like patterns to humans. This observation has led to the argument that deep visual…

Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…

Machine learning models, especially deep neural networks (DNNs), have been shown to be vulnerable against adversarial examples which are carefully crafted samples with a small magnitude of the perturbation. Such adversarial perturbations…

Adversarial examples -- inputs with imperceptible perturbations that fool neural networks -- remain one of deep learning's most perplexing phenomena despite nearly a decade of research. While numerous defenses and explanations have been…

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

Despite the remarkable success of deep neural networks, significant concerns have emerged about their robustness to adversarial perturbations to inputs. While most attacks aim to ensure that these are imperceptible, physical perturbation…

Advances in the effectiveness of machine learning models have come at the cost of enormous complexity resulting in a poor understanding of how they function. Local surrogate methods have been used to approximate the workings of these…