Alexander Levine

According to our database, Alexander Levine authored at least 23 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Multistep Inverse Is Not All You Need.

Alexander Levine, Peter Stone, Amy Zhang

CoRR, 2024

2023

Scalable Methods for Robust Machine Learning.

Alexander Levine

PhD thesis, 2023

Provable Robustness against Wasserstein Distribution Shifts via Input Randomization.

Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Goal-Conditioned Q-learning as Knowledge Distillation.

Alexander Levine, Soheil Feizi

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Invariant Learning via Diffusion Dreamed Distribution Shifts.

Priyatham Kattakinda, Alexander Levine, Soheil Feizi

CoRR, 2022

Certifying Model Accuracy under Distribution Shifts.

Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi

CoRR, 2022

Lethal Dose Conjecture on Data Poisoning.

Wenxiao Wang, Alexander Levine, Soheil Feizi

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

Wenxiao Wang, Alexander Levine, Soheil Feizi

Proceedings of the International Conference on Machine Learning, 2022

Policy Smoothing for Provably Robust Reinforcement Learning.

Aounon Kumar, Alexander Levine, Soheil Feizi

Proceedings of the Tenth International Conference on Learning Representations, 2022

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

Jiang Liu, Alexander Levine, Chun Pong Lau, Rama Chellappa, Soheil Feizi

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Provable Adversarial Robustness for Fractional Lp Threat Models.

Alexander Levine, Soheil Feizi

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Improved, Deterministic Smoothing for L1 Certified Robustness.

Alexander Levine, Soheil Feizi

CoRR, 2021

Improved, Deterministic Smoothing for L₁ Certified Robustness.

Alexander Levine, Soheil Feizi

Proceedings of the 38th International Conference on Machine Learning, 2021

Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks.

Alexander Levine, Soheil Feizi

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Tight Second-Order Certificates for Randomized Smoothing.

Alexander Levine, Aounon Kumar, Thomas A. Goldstein, Soheil Feizi

CoRR, 2020

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks.

Alexander Levine, Soheil Feizi

CoRR, 2020

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

Wei-An Lin, Chun Pong Lau, Alexander Levine, Rama Chellappa, Soheil Feizi

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Certifying Confidence via Randomized Smoothing.

Aounon Kumar, Alexander Levine, Soheil Feizi, Tom Goldstein

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

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

Alexander Levine, Soheil Feizi

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness.

Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi

Proceedings of the 37th International Conference on Machine Learning, 2020

Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks.

Alexander Levine, Soheil Feizi

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation.

Alexander Levine, Soheil Feizi

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Certifiably Robust Interpretation in Deep Learning.

Alexander Levine, Sahil Singla, Soheil Feizi

CoRR, 2019