Aounon Kumar
9 papers · 2020–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver π Academic Marathon Β· Sprint πΊοΈ Taxonomy Completionist (22) π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze
π§¬
Topic Evolution
π₯
Unstoppable Β· Bronze
Venues
Top co-authors
Research topics
Artificial Intelligence
(8)
Machine Learning
(8)
Core AI
(8)
Learning Types
(4)
Optimization & Theory
(4)
Application Areas
(3)
Core Methods
(2)
Computer Vision
(1)
Deep Learning
(1)
Healthcare & Medicine
(1)
Natural Language Processing
(1)
Analysis
(1)
Clinical
(1)
Learning Paradigms
(1)
Models
(1)
Keywords
adversarial robustness
(6)
randomized smoothing
(5)
certified robustness
(4)
adversarial learning
(1)
image generation
(1)
object detection
(1)
deepfake detection
(1)
responsible ai
(1)
neyman-pearson lemma
(1)
distribution shift
(1)
curse of dimensionality
(1)
structured output
(1)
gaussian noise
(1)
diffusion model
(1)
adversarial defense
(1)
benchmark dataset
(1)
adversarial perturbation
(1)
metric space
(1)
model fine-tuning
(1)
watermark detection
(1)
Papers
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
ACL 2026
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
NeurIPS 2024
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
ICLR 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
NeurIPS 2021
Certifying Confidence via Randomized Smoothing
NeurIPS 2020
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
ICML 2020
Detection as Regression: Certified Object Detection with Median Smoothing
NeurIPS 2020