Aounon Kumar
9 papers · 2020–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (3) π Interdisciplinary Bridge π Cross-Pollinator (13)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(16)
π₯
Unstoppable
(5)
Conferences
NIPS (4)
ICLR (3)
ACL (1)
ICML (1)
Top co-authors
Keywords
randomized smoothing
(4)
adversarial robustness
(4)
certified robustness
(3)
neyman-pearson lemma
(1)
curse of dimensionality
(1)
structured output
(1)
adversarial defense
(1)
benchmark dataset
(1)
adversarial perturbation
(1)
metric space
(1)
model fine-tuning
(1)
weak-to-strong generalization
(1)
medical safety
(1)
confidence estimation
(1)
out-of-distribution robustness
(1)
model fairness
(1)
certifiable robustness
(1)
large language model
(1)
isotropic gaussian
(1)
prediction margin
(1)
Papers
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
ACL 2026
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
ICLR 2024
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
NIPS 2024
Provable Robustness against Wasserstein Distribution Shifts via Input Randomization
ICLR 2023
Policy Smoothing for Provably Robust Reinforcement Learning
ICLR 2022
Center Smoothing: Certified Robustness for Networks with Structured Outputs
NIPS 2021
Detection as Regression: Certified Object Detection with Median Smoothing
NIPS 2020
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
ICML 2020
Certifying Confidence via Randomized Smoothing
NIPS 2020