相关论文: Certifiably Robust Interpretation in Deep Learning

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code…

Certified defenses such as randomized smoothing have shown promise towards building reliable machine learning systems against $\ell_p$-norm bounded attacks. However, existing methods are insufficient or unable to provably defend against…

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial…

Deep learning methods have gained increased attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper use of data artifacts and the accurate problem formulation of…

Deep Learning NLP domain lacks procedures for the analysis of model robustness. In this paper we propose a framework which validates robustness of any Question Answering model through model explainers. We propose that a robust model should…

We consider the problem of learning a graph from a finite set of noisy graph signal observations, the goal of which is to find a smooth representation of the graph signal. Such a problem is motivated by the desire to infer relational…

Patch robustness certification is an emerging verification approach for defending against adversarial patch attacks with provable guarantees for deep learning systems. Certified recovery techniques guarantee the prediction of the sole true…

Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the…

While prior research has proposed a plethora of methods that build neural classifiers robust against adversarial robustness, practitioners are still reluctant to adopt them due to their unacceptably severe clean accuracy penalties. This…

Interpretability of Deep Learning (DL) is a barrier to trustworthy AI. Despite great efforts made by the Explainable AI (XAI) community, explanations lack robustness -- indistinguishable input perturbations may lead to different XAI…

There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed to defend against…

Improving the interpretability of geospatial artificial intelligence (GeoAI) models has become critically important to open the "black box" of complex AI models, such as deep learning. This paper compares popular saliency map generation…

Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision boundaries. This paper…

Certifiable robustness gives the guarantee that small perturbations around an input to a classifier will not change the prediction. There are two approaches to provide certifiable robustness to adversarial examples: a) explicitly training…

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their…

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…

Adversarial perturbations are imperceptible changes to input pixels that can change the prediction of deep learning models. Learned weights of models robust to such perturbations are previously found to be transferable across different…