3 papers
cs.LG2020
Adversarial Attacks on Binary Image Recognition Systems
Eric Balkanski, Harrison Chase, Kojin Oshiba +3
We initiate the study of adversarial attacks on models for binary (i.e. black and white) image classification. Although there has been a great deal of work on attacking models for…
cs.LG2019
Predicting Choice with Set-Dependent Aggregation
Nir Rosenfeld, Kojin Oshiba, Yaron Singer
Providing users with alternatives to choose from is an essential component in many online platforms, making the accurate prediction of choice vital to their success. A renewed inte…
stat.ML2018
Robust Classification of Financial Risk
Suproteem K. Sarkar, Kojin Oshiba, Daniel Giebisch +1
Algorithms are increasingly common components of high-impact decision-making, and a growing body of literature on adversarial examples in laboratory settings indicates that standar…