78 citations · 123 across the 11 of their papers we have counts for
11 papers
Is Certifying Robustness Still Worthwhile?
Ravi Mangal, Klas Leino, Zifan Wang +5
Over the years, researchers have developed myriad attacks that exploit the ubiquity of adversarial examples, as well as defenses that aim to guard against the security vulnerabilit…
Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models
Kaiji Lu, Anupam Datta
Previous works show that deep NLP models are not always conceptually sound: they do not always learn the correct linguistic concepts. Specifically, they can be insensitive to word…
Faithful Explanations for Deep Graph Models
Zifan Wang, Yuhang Yao, Chaoran Zhang +5
This paper studies faithful explanations for Graph Neural Networks (GNNs). First, we provide a new and general method for formally characterizing the faithfulness of explanations f…
Consistent Counterfactuals for Deep Models
Emily Black, Zifan Wang, Matt Fredrikson +1
Counterfactual examples are one of the most commonly-cited methods for explaining the predictions of machine learning models in key areas such as finance and medical diagnosis. Cou…
Robust Models Are More Interpretable Because Attributions Look Normal
Zifan Wang, Matt Fredrikson, Anupam Datta
Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more conc…
Influence Patterns for Explaining Information Flow in BERT
Kaiji Lu, Zifan Wang, Piotr Mardziel +1
While attention is all you need may be proving true, we do not know why: attention-based transformer models such as BERT are superior but how information flows from input tokens to…
Fairness Under Feature Exemptions: Counterfactual and Observational Measures
Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel +2
With the growing use of ML in highly consequential domains, quantifying disparity with respect to protected attributes, e.g., gender, race, etc., is important. While quantifying di…
Interpreting Interpretations: Organizing Attribution Methods by Criteria
Zifan Wang, Piotr Mardziel, Anupam Datta +1
Motivated by distinct, though related, criteria, a growing number of attribution methods have been developed tointerprete deep learning. While each relies on the interpretability o…
Feature-Wise Bias Amplification
Klas Leino, Emily Black, Matt Fredrikson +2
We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth.…
Influence in Classification via Cooperative Game Theory
Amit Datta, Anupam Datta, Ariel D. Procaccia +1
A dataset has been classified by some unknown classifier into two types of points. What were the most important factors in determining the classification outcome? In this work, we…
Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discrimination
Amit Datta, Michael Carl Tschantz, Anupam Datta
To partly address people's concerns over web tracking, Google has created the Ad Settings webpage to provide information about and some choice over the profiles Google creates on u…