research
∙
07/05/2023
Gaussian Database Alignment and Gaussian Planted Matching
Database alignment is a variant of the graph alignment problem: Given a ...
share
research
∙
02/21/2023
Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker
Finding classifiers robust to adversarial examples is critical for their...
research
∙
04/16/2021
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Understanding the fundamental limits of robust supervised learning has e...
research
∙
09/26/2019
Lower Bounds on Adversarial Robustness from Optimal Transport
While progress has been made in understanding the robustness of machine ...
research
∙
05/05/2019
Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
A large body of recent work has investigated the phenomenon of evasion a...
research
∙
03/04/2019
Database Alignment with Gaussian Features
We consider the problem of aligning a pair of databases with jointly Gau...
research
∙
09/10/2018
Partial Recovery of Erdős-Rényi Graph Alignment via k-Core Alignment
We determine information theoretic conditions under which it is possible...
research
∙
06/05/2018
PAC-learning in the presence of evasion adversaries
The existence of evasion attacks during the test phase of machine learni...
research
∙
05/10/2018
Fundamental Limits of Database Alignment
We consider the problem of aligning a pair of databases with correlated ...
research
∙
04/25/2018