Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning

Published in Neurips 20, 2020

Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training. The goal of a backdoor is to corrupt the performance of the trained model on specific sub-tasks (e.g., by classifying green cars as frogs)

Recommended citation: Wang H, Sreenivasan K, Rajput S, Vishwakarma H, Agarwal S, Sohn JY, Lee K, Papailiopoulos D. Attack of the tails: Yes, you really can backdoor federated learning. arXiv preprint arXiv:2007.05084. 2020 Jul 9. https://papers.nips.cc/paper/2020/file/b8ffa41d4e492f0fad2f13e29e1762eb-Paper.pdf

teaching

Fall 2018: CS/MA 240: Discrete Mathematics

Undergraduate course, UW-Madison, Computer Science, 2018

I was a teaching assistant to the instructor: Beck Hasti

Spring 2019: CS/MA 435: Intro to Cryptography

Undergraduate course, UW-Madison, Computer Science, 2019

I was a teaching assistant to the instructor: Prof. Eric Bach

Fall 2019: CS 577: Intro to Algorithms