Zijie J. Wang

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

2020

Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully-crafted perturbations on data inputs that can fool a model into making incorrect predictions. Despite significant research …

Visual Auditor: Interactive Visualization for Detection and Summarization of Model Biases

2022 · arXiv (Cornell University)

As machine learning (ML) systems become increasingly widespread, it is necessary to audit these systems for biases prior to their deployment. Recent research has developed algorithms for effectively identifying intersectional bias in the form of …