Alexander Levine

发表

Policy Smoothing for Provably Robust Reinforcement Learning pdf

Alexander Levine, Soheil Feizi, Aounon Kumar, 2021, ArXiv.

Certifying Confidence via Randomized Smoothing

T. Goldstein, Aounon Kumar, Alexander Levine, 2020, NeurIPS.

(De)Randomized Smoothing for Certifiable Defense against Patch Attacks

Alexander Levine, S. Feizi, 2020, NeurIPS.

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks pdf

Alexander Levine, Soheil Feizi, Alexander Levine, 2020, ICLR.

Certifying Model Accuracy under Distribution Shifts

T. Goldstein, Aounon Kumar, Alexander Levine, 2022, ArXiv.

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection pdf

Rama Chellappa, Alexander Levine, Soheil Feizi, 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Policy Smoothing for Provably Robust Reinforcement Learning

Aounon Kumar, Alexander Levine, S. Feizi, 2021, ICLR.

Invariant Learning via Diffusion Dreamed Distribution Shifts

Alexander Levine, S. Feizi, Priyatham Kattakinda, 2022, ArXiv.

Goal-Conditioned Q-Learning as Knowledge Distillation

Alexander Levine, S. Feizi, 2022, ArXiv.

Goal-Conditioned Q-Learning as Knowledge Distillation

Alexander Levine, S. Feizi, 2022, AAAI.

Certifiably Robust Interpretation in Deep Learning pdf

Alexander Levine, Sahil Singla, Soheil Feizi, 2019, ArXiv.

Improved, Deterministic Smoothing for L1 Certified Robustness

Alexander Levine, Soheil Feizi, Alexander Levine, 2021, ICML.

Certifying Confidence via Randomized Smoothing pdf

Tom Goldstein, Alexander Levine, Soheil Feizi, 2020, NeurIPS.

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness

Tom Goldstein, Soheil Feizi, Aounon Kumar, 2020, ICML.

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks pdf

Wei-An Lin, Rama Chellappa, Alexander Levine, 2020, NeurIPS.

(De)Randomized Smoothing for Certifiable Defense against Patch Attacks pdf

Alexander Levine, Soheil Feizi, Alexander Levine, 2020, NeurIPS.

Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation

Alexander Levine, S. Feizi, Wenxiao Wang, 2022, ICML.

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks pdf

Alexander Levine, Soheil Feizi, Alexander Levine, 2020, ICLR.

Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks

Soheil Feizi, Alexander Levine, Alexander Levine, 2019, AISTATS.

Lethal Dose Conjecture on Data Poisoning

Alexander Levine, S. Feizi, Wenxiao Wang, 2022, NeurIPS.

Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation

Alexander Levine, Soheil Feizi, Alexander Levine, 2019, AAAI.

Tight Second-Order Certificates for Randomized Smoothing

Aounon Kumar, Alexander Levine, S. Feizi, 2020, ArXiv.

Certifying Model Accuracy under Distribution Shifts

T. Goldstein, Aounon Kumar, Alexander Levine, 2022, arXiv.org.

Bounds and Approximations for Maximum Leaf Spanning Tree

Alexander Levine, Marina Knittel, Yusuf Alnawakhtha, 2018 .

Provable Robustness against Wasserstein Distribution Shifts via Input Randomization

T. Goldstein, Aounon Kumar, Alexander Levine, 2023, ICLR.