Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Soheil Feizi

Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings


Aug 30, 2021
Mazda Moayeri, Soheil Feizi

* Accepted to ICCV 2021 

  Access Paper or Ask Questions

Householder Activations for Provable Robustness against Adversarial Attacks


Aug 05, 2021
Sahil Singla, Surbhi Singla, Soheil Feizi


  Access Paper or Ask Questions

Policy Smoothing for Provably Robust Reinforcement Learning


Jun 21, 2021
Aounon Kumar, Alexander Levine, Soheil Feizi


  Access Paper or Ask Questions

Skew Orthogonal Convolutions


May 24, 2021
Sahil Singla, Soheil Feizi


  Access Paper or Ask Questions

Understanding Overparameterization in Generative Adversarial Networks


Apr 12, 2021
Yogesh Balaji, Mohammadmahdi Sajedi, Neha Mukund Kalibhat, Mucong Ding, Dominik Stöger, Mahdi Soltanolkotabi, Soheil Feizi

* Accepted in ICLR 2021 

  Access Paper or Ask Questions

Improved, Deterministic Smoothing for L1 Certified Robustness


Mar 17, 2021
Alexander Levine, Soheil Feizi


  Access Paper or Ask Questions

Low Curvature Activations Reduce Overfitting in Adversarial Training


Feb 15, 2021
Vasu Singla, Sahil Singla, David Jacobs, Soheil Feizi


  Access Paper or Ask Questions

Benchmarking Deep Learning Interpretability in Time Series Predictions


Oct 26, 2020
Aya Abdelsalam Ismail, Mohamed Gunady, Héctor Corrada Bravo, Soheil Feizi

* NeurIPS 2020 

  Access Paper or Ask Questions

Tight Second-Order Certificates for Randomized Smoothing


Oct 20, 2020
Alexander Levine, Aounon Kumar, Thomas Goldstein, Soheil Feizi


  Access Paper or Ask Questions

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation


Oct 12, 2020
Yogesh Balaji, Rama Chellappa, Soheil Feizi

* Accepted in NeurIPS 2020. Code available at https://github.com/yogeshbalaji/robustOT 

  Access Paper or Ask Questions

Winning Lottery Tickets in Deep Generative Models


Oct 05, 2020
Neha Mukund Kalibhat, Yogesh Balaji, Soheil Feizi


  Access Paper or Ask Questions

GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue


Sep 24, 2020
Pirazh Khorramshahi, Hossein Souri, Rama Chellappa, Soheil Feizi


  Access Paper or Ask Questions

Certifying Confidence via Randomized Smoothing


Sep 17, 2020
Aounon Kumar, Alexander Levine, Soheil Feizi, Tom Goldstein


  Access Paper or Ask Questions

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


Sep 05, 2020
Wei-An Lin, Chun Pong Lau, Alexander Levine, Rama Chellappa, Soheil Feizi


  Access Paper or Ask Questions

Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning


Jul 02, 2020
Vedant Nanda, Samuel Dooley, Sahil Singla, Soheil Feizi, John P. Dickerson

* 18 pages, 17 figures; Under review 

  Access Paper or Ask Questions

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks


Jun 26, 2020
Alexander Levine, Soheil Feizi


  Access Paper or Ask Questions

Influence Functions in Deep Learning Are Fragile


Jun 25, 2020
Samyadeep Basu, Philip Pope, Soheil Feizi

* Under Review 

  Access Paper or Ask Questions

Perceptual Adversarial Robustness: Defense Against Unseen Threat Models


Jun 22, 2020
Cassidy Laidlaw, Sahil Singla, Soheil Feizi


  Access Paper or Ask Questions

Second-Order Provable Defenses against Adversarial Attacks


Jun 01, 2020
Sahil Singla, Soheil Feizi

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

  Access Paper or Ask Questions

Subadditivity of Probability Divergences on Bayes-Nets with Applications to Time Series GANs


Mar 02, 2020
Mucong Ding, Constantinos Daskalakis, Soheil Feizi


  Access Paper or Ask Questions

(De)Randomized Smoothing for Certifiable Defense against Patch Attacks


Feb 25, 2020
Alexander Levine, Soheil Feizi


  Access Paper or Ask Questions

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness


Feb 08, 2020
Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi


  Access Paper or Ask Questions

Playing it Safe: Adversarial Robustness with an Abstain Option


Nov 25, 2019
Cassidy Laidlaw, Soheil Feizi


  Access Paper or Ask Questions

Bounding Singular Values of Convolution Layers


Nov 22, 2019
Sahil Singla, Soheil Feizi


  Access Paper or Ask Questions

Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation


Nov 21, 2019
Alexander Levine, Soheil Feizi


  Access Paper or Ask Questions

Adversarial Robustness of Flow-Based Generative Models


Nov 20, 2019
Phillip Pope, Yogesh Balaji, Soheil Feizi


  Access Paper or Ask Questions

Second-Order Group Influence Functions for Black-Box Predictions


Nov 01, 2019
Samyadeep Basu, Xuchen You, Soheil Feizi


  Access Paper or Ask Questions

Quantum Wasserstein Generative Adversarial Networks


Oct 31, 2019
Shouvanik Chakrabarti, Yiming Huang, Tongyang Li, Soheil Feizi, Xiaodi Wu

* Accepted to the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019). Codes are available at https://github.com/yiminghwang/qWGAN 

  Access Paper or Ask Questions

Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks


Oct 27, 2019
Aya Abdelsalam Ismail, Mohamed Gunady, Luiz Pessoa, Héctor Corrada Bravo, Soheil Feizi

* Neurips 2019 

  Access Paper or Ask Questions