相关论文: Exploiting the Relationship Between Kendall's Rank…

We show new connections between adversarial learning and explainability for deep neural networks (DNNs). One form of explanation of the output of a neural network model in terms of its input features, is a vector of feature-attributions.…

Neural network interpretation methods, particularly feature attribution methods, are known to be fragile with respect to adversarial input perturbations. To address this, several methods for enhancing the local smoothness of the gradient…

The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this work, we show that…

Model attribution is a critical component of deep neural networks (DNNs) for its interpretability to complex models. Recent studies bring up attention to the security of attribution methods as they are vulnerable to attribution attacks that…

Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally…

Deep neural networks are the default choice of learning models for computer vision tasks. Extensive work has been carried out in recent years on explaining deep models for vision tasks such as classification. However, recent work has shown…

Deep neural networks (DNNs) have had many successes, but they suffer from two major issues: (1) a vulnerability to adversarial examples and (2) a tendency to elude human interpretation. Interestingly, recent empirical and theoretical…

Attribution methods are primarily designed to study input component contributions to individual model predictions. However, some research applications require a summary of attribution patterns across the entire dataset to facilitate the…

An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our…

Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely on two important techniques: input attribution for hindsight analysis and network compression to reduce its size for…

Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties -- most…

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions…

As deep learning (DL) efficacy grows, concerns for poor model explainability grow also. Attribution methods address the issue of explainability by quantifying the importance of an input feature for a model prediction. Among various methods,…

Deep Neural Network classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-explored. In this…

Model attribution is a popular tool to explain the rationales behind model predictions. However, recent work suggests that the attributions are vulnerable to minute perturbations, which can be added to input samples to fool the attributions…

Explaining deep learning models in a way that humans can easily understand is essential for responsible artificial intelligence applications. Attribution methods constitute an important area of explainable deep learning. The attribution…

We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. Regularization is key in deep learning, especially when training complex models on relatively small…

Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it has been shown that the…

In this paper, we present an approach for evaluating attribution maps, which play a central role in interpreting the predictions of convolutional neural networks (CNNs). We show that the widely used insertion/deletion metrics are…

Source code attribution approaches have achieved remarkable accuracy thanks to the rapid advances in deep learning. However, recent studies shed light on their vulnerability to adversarial attacks. In particular, they can be easily deceived…