activity
20202022
most citedGreen Lighting ML: Confidentiality, Integrity, and Availability of Machine Learning Systems in Deployment

3 citations · 11 across the 10 of their papers we have counts for

collaborators

10 papers

cs.LG20222 cited

Robustness and Usefulness in AI Explanation Methods

Erick Galinkin

Explainability in machine learning has become incredibly important as machine learning-powered systems become ubiquitous and both regulation and public sentiment begin to demand an…

cs.AI20223 cited

Towards a Responsible AI Development Lifecycle: Lessons From Information Security

Erick Galinkin

Legislation and public sentiment throughout the world have promoted fairness metrics, explainability, and interpretability as prescriptions for the responsible development of ethic…

cs.LG2021

Who's Afraid of Thomas Bayes?

Erick Galinkin

In many cases, neural networks perform well on test data, but tend to overestimate their confidence on out-of-distribution data. This has led to adoption of Bayesian neural network…

cs.CY20211 cited

The State of AI Ethics Report (January 2021)

Abhishek Gupta, Alexandrine Royer, Connor Wright +9

The 3rd edition of the Montreal AI Ethics Institute's The State of AI Ethics captures the most relevant developments in AI Ethics since October 2020. It aims to help anyone, from m…

cs.CR20211 cited

The Influence of Dropout on Membership Inference in Differentially Private Models

Erick Galinkin

Differentially private models seek to protect the privacy of data the model is trained on, making it an important component of model security and privacy. At the same time, data sc…

cs.CR2021

Information Security Games: A Survey

Erick Galinkin

We introduce some preliminaries about game theory and information security. Then surveying a subset of the literature, we identify opportunities for future research.