Aounon Kumar | DeepAI

DeepAI AI Chat

Featured Co-authors

Tom Goldstein
140 publications
Soheil Feizi
76 publications
Chirag Agarwal
24 publications
Suraj Srinivas
20 publications
John Dickerson
18 publications
Alexander Levine
16 publications
Ping-Yeh Chiang
14 publications
Melanie Schmidt
12 publications
Samir Khuller
10 publications
Ahmed Abdelkader
9 publications
Michael J. Curry
7 publications

∙ 09/06/2023

Certifying LLM Safety against Adversarial Prompting

Large language models (LLMs) released for public use incorporate guardra...

0 Aounon Kumar, et al. ∙

∙ 03/28/2023

Provable Robustness for Streaming Models with a Sliding Window

The literature on provable robustness in machine learning has primarily ...

0 Aounon Kumar, et al. ∙

∙ 01/28/2022

Certifying Model Accuracy under Distribution Shifts

Certified robustness in machine learning has primarily focused on advers...

0 Aounon Kumar, et al. ∙

∙ 06/21/2021

Policy Smoothing for Provably Robust Reinforcement Learning

The study of provable adversarial robustness for deep neural network (DN...

0 Aounon Kumar, et al. ∙

∙ 02/19/2021

Center Smoothing for Certifiably Robust Vector-Valued Functions

Randomized smoothing has been successfully applied in high-dimensional i...

0 Aounon Kumar, et al. ∙

∙ 10/20/2020

Tight Second-Order Certificates for Randomized Smoothing

Randomized smoothing is a popular way of providing robustness guarantees...

0 Alexander Levine, et al. ∙

∙ 09/17/2020

Certifying Confidence via Randomized Smoothing

Randomized smoothing has been shown to provide good certified-robustness...

0 Aounon Kumar, et al. ∙

∙ 07/07/2020

Detection as Regression: Certified Object Detection by Median Smoothing

Despite the vulnerability of object detectors to adversarial attacks, ve...

0 Ping-Yeh Chiang, et al. ∙

∙ 02/08/2020

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness

Randomized smoothing, using just a simple isotropic Gaussian distributio...

0 Aounon Kumar, et al. ∙

∙ 11/26/2018

On the cost of essentially fair clusterings

Clustering is a fundamental tool in data mining. It partitions points in...

0 Ioana O. Bercea, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world