Related papers: Robust Ranking Explanations
This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…
Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of…
We consider the problem of the stability of saliency-based explanations of Neural Network predictions under adversarial attacks in a classification task. Saliency interpretations of deterministic Neural Networks are remarkably brittle even…
Adversarial attacks have been widely studied for general classification tasks, but remain unexplored in the context of fine-grained recognition, where the inter-class similarities facilitate the attacker's task. In this paper, we identify…
Algorithms are increasingly common components of high-impact decision-making, and a growing body of literature on adversarial examples in laboratory settings indicates that standard machine learning models are not robust. This suggests that…
In this work, we investigate the phenomenon that robust image classifiers have human-recognizable features -- often referred to as interpretability -- as revealed through the input gradients of their score functions and their subsequent…
Recently, it has been widely known that deep neural networks are highly vulnerable and easily broken by adversarial attacks. To mitigate the adversarial vulnerability, many defense algorithms have been proposed. Recently, to improve…
An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing…
Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we…
In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic…
Graph Neural Networks (GNNs) have become a cornerstone in graph-based data analysis, with applications in diverse domains such as bioinformatics, social networks, and recommendation systems. However, the interplay between model…
With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted approaches for model interpretability is feature-based…
Classification models are very sensitive to data uncertainty, and finding robust classifiers that are less sensitive to data uncertainty has raised great interest in the machine learning literature. This paper aims to construct robust…
Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing…
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples. Although this problem has been widely studied empirically, much remains unknown concerning…
Reinforcement Learning (RL) has shown remarkable success in solving relatively complex tasks, yet the deployment of RL systems in real-world scenarios poses significant challenges related to safety and robustness. This paper aims to…
In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a neural model incorporating a human inspired, visual attention…
This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Training leads to robust models, whose learnt features appear to…
Recently, RobustBench (Croce et al. 2020) has become a widely recognized benchmark for the adversarial robustness of image classification networks. In its most commonly reported sub-task, RobustBench evaluates and ranks the adversarial…
Neural networks are very successful at detecting patterns in noisy data, and have become the technology of choice in many fields. However, their usefulness is hampered by their susceptibility to adversarial attacks. Recently, many methods…