Aounon Kumar
AI/ML Researcher
I am a Postdoc at Harvard University working in Trustworthy AI
with Professor Himabindu Lakkaraju. My research focuses on the safety
, security
, and robustness
of machine learning (ML) models. It involves designing algorithms to certifiably defend models against adversarial inputs, for example, safeguarding large language models (LLMs) from prompts that circumvent safety guardrails. I have studied and contributed to model robustness in several machine learning domains including computer vision
, reinforcement learning
, and natural language processing
. My work has been accepted in prominent ML conferences such as ICML
, ICLR
and NeurIPS
, and I am actively involved in collaborative projects within the academic community.
Media Coverage: My recent works on LLM safety
and reliability
have been featured in popular tech magazines and academic news outlets:
- Science News Magazine, D^3 Institute at Harvard. Work featured: Certifying LLM Safety against Adversarial Prompting.
- The Washington Post, Bloomberg, Wired, New Scientist, The Register, TechSpot. Work featured: Can AI-Generated Text be Reliably Detected?.
Before joining Harvard, I completed my PhD at the University of Maryland in certified robustness
in machine learning (see my dissertation here). I was fortunate to be advised by Professors Soheil Feizi and Tom Goldstein. During my PhD, I have spent time as a research intern at Nokia Bell Labs and an applied scientist intern at Amazon, where I worked on network security-related machine learning applications and uncertainty estimation for human action recognition models. I have also served as a reviewer for machine learning conferences such as ICML and NeurIPS.
I did my undergraduate studies at IIT Mandi and my master’s at IIT Delhi, where I studied a wide range of topics in computer science such as machine learning, advanced algorithms, combinatorial optimization, complexity theory and cryptography. My master’s thesis was on the computational hardness of approximating the optimal solution of a variant of the k-center clustering problem.
News
Feb 12, 2024 | New pre-print on Certifying LLM Safety against Adversarial Prompting! Covered by Science News Magazine. |
Dec 19, 2023 | Graduated from UMD ! |
Oct 05, 2023 | Started as a Research Associate at Harvard University . |
Selected Publications
See full list at Google Scholar.
Preprint | Certifying LLM Safety against Adversarial Prompting Aounon Kumar, Chirag Agarwal, Suraj Srinivas, Aaron Jiaxun Li, Soheil Feizi, Himabindu Lakkaraju ArXiv, Code, PDF Media Coverage: Science News Magazine, D^3 Institute at Harvard. |
Preprint | Can AI-Generated Text be Reliably Detected? Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, Soheil Feizi ArXiv, Code, PDF Media Coverage: The Washington Post, Bloomberg, Wired, New Scientist, The Register, TechSpot. |
ICLR 2023 | Provable Robustness against Wasserstein Distribution Shifts via Input Randomization Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi OpenReview, ArXiv, Code, PDF |
ICLR 2022 | Policy Smoothing for Provably Robust Reinforcement Learning Aounon Kumar, Alexander Levine, Soheil Feizi OpenReview, ArXiv, Code, PDF |
ICML 2020 | Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi ICML Proceedings, ArXiv, Code, PDF |
NeurIPS 2021 | Center Smoothing: Provable Robustness for Functions with Structured Outputs Aounon Kumar, Tom Goldstein NeurIPS Proceedings, ArXiv, Code, PDF |
Contact
Science and Engineering Complex
150 Western Ave
Office #6220
Allston, MA 02134