activity
20152021
most citedUnderstanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

5 citations · 11 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG20215 cited

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen +1

Unsupervised domain adaptation (UDA) enables cross-domain learning without target domain labels by transferring knowledge from a labeled source domain whose distribution differs fr…

cs.LG20213 cited

Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks

Byunggill Joe, Akshay Mehra, Insik Shin +1

Electronic Health Records (EHRs) provide a wealth of information for machine learning algorithms to predict the patient outcome from the data including diagnostic information, vita…

cs.LG2020

Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection

Byunggill Joe, Jihun Hamm, Sung Ju Hwang +2

Although deep neural networks have shown promising performances on various tasks, they are susceptible to incorrect predictions induced by imperceptibly small perturbations in inpu…

cs.LG2020

How Robust are Randomized Smoothing based Defenses to Data Poisoning?

Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen +1

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a…

cs.LG2018

K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning

Jihun Hamm, Yung-Kyun Noh

Minimax optimization plays a key role in adversarial training of machine learning algorithms, such as learning generative models, domain adaptation, privacy preservation, and robus…

cs.LG2018

Fast Interactive Image Retrieval using large-scale unlabeled data

Akshay Mehra, Jihun Hamm, Mikhail Belkin

An interactive image retrieval system learns which images in the database belong to a user's query concept, by analyzing the example images and feedback provided by the user. The c…