Alexander Levine
13 papers · 2020–2025 · 6 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 ↓+5 more ↓ Show less ↑
π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (27) π Interdisciplinary Bridge Β· Bronze
π
Grand Slam
π€
Dynamic Duo
(12)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(57)
Top co-authors
Research topics
Machine Learning
(12)
Learning Types Β· Machine Learning
(9)
Artificial Intelligence
(8)
Optimization & Theory
(7)
Core AI Β· Artificial Intelligence
(6)
Application Areas
(5)
Deep Learning
(3)
Core Methods
(2)
Learning Paradigms
(2)
Learning Types Β· Deep Learning
(2)
Computer Vision
(1)
Reinforcement Learning
(1)
Analysis
(1)
Core AI Β· Computer Vision
(1)
Methods
(1)
Keywords
adversarial robustness
(8)
randomized smoothing
(6)
certified robustness
(5)
adversarial defense
(3)
reinforcement learning
(2)
wasserstein distance
(2)
off-policy learning
(1)
neyman-pearson lemma
(1)
data poisoning
(1)
adversarial training
(1)
generative model
(1)
distribution shift
(1)
sample complexity
(1)
curse of dimensionality
(1)
adversarial attack
(1)
knowledge distillation
(1)
gaussian noise
(1)
image manifold
(1)
off-policy reinforcement learning
(1)
object detection
(1)
Papers
Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory
ICLR 2025
Goal-Conditioned Q-learning as Knowledge Distillation
AAAI 2023
Provable Robustness against Wasserstein Distribution Shifts via Input Randomization
ICLR 2023
Lethal Dose Conjecture on Data Poisoning
NeurIPS 2022
Policy Smoothing for Provably Robust Reinforcement Learning
ICLR 2022
Segment and Complete: Defending Object Detectors Against Adversarial Patch Attacks With Robust Patch Detection
CVPR 2022
Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks
ICLR 2021
Certifying Confidence via Randomized Smoothing
NeurIPS 2020
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
ICML 2020
(De)Randomized Smoothing for Certifiable Defense against Patch Attacks
NeurIPS 2020
Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks
NeurIPS 2020
Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation
AAAI 2020
Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks
AISTATS 2020