activity
20172024
most citedConsistent Counterfactuals for Deep Models

7 citations · 26 across the 12 of their papers we have counts for

collaborators
Showing 2018Show all

6 papers · 1 filter

cs.LG2018

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.…

cs.LG2018

Hunting for Discriminatory Proxies in Linear Regression Models

Samuel Yeom, Anupam Datta, Matt Fredrikson

A machine learning model may exhibit discrimination when used to make decisions involving people. One potential cause for such outcomes is that the model uses a statistical proxy f…

cs.CR2018

Contextual and Granular Policy Enforcement in Database-backed Applications

Abhishek Bichhawat, Matt Fredrikson, Jean Yang +1

Database-backed applications rely on inlined policy checks to process users' private and confidential data in a policy-compliant manner as traditional database access control mecha…

cs.LG2018

Supervising Feature Influence

Shayak Sen, Piotr Mardziel, Anupam Datta +1

Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their bias…

cs.LG2018

Influence-Directed Explanations for Deep Convolutional Networks

Klas Leino, Shayak Sen, Anupam Datta +2

We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peerin…

cs.PL2018

Verifying and Synthesizing Constant-Resource Implementations with Types

Van Chan Ngo, Mario Dehesa-Azuara, Matthew Fredrikson +1

We propose a novel type system for verifying that programs correctly implement constant-resource behavior. Our type system extends recent work on automatic amortized resource analy…