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 Sven Gowal

Data Augmentation Can Improve Robustness


Nov 09, 2021
Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann

* Accepted at NeurIPS 2021. arXiv admin note: substantial text overlap with arXiv:2103.01946; text overlap with arXiv:2110.09468 

  Access Paper or Ask Questions

A Fine-Grained Analysis on Distribution Shift


Oct 21, 2021
Olivia Wiles, Sven Gowal, Florian Stimberg, Sylvestre Alvise-Rebuffi, Ira Ktena, Krishnamurthy, Dvijotham, Taylan Cemgil


  Access Paper or Ask Questions

Improving Robustness using Generated Data


Oct 18, 2021
Sven Gowal, Sylvestre-Alvise Rebuffi, Olivia Wiles, Florian Stimberg, Dan Andrei Calian, Timothy Mann

* Accepted at NeurIPS 2021 

  Access Paper or Ask Questions

An Empirical Investigation of Learning from Biased Toxicity Labels


Oct 04, 2021
Neel Nanda, Jonathan Uesato, Sven Gowal

* 8 pages, 6 figures. Accepted to the Socially Responsible Machine Learning Workshop, ICML 2021 

  Access Paper or Ask Questions

A Closer Look at the Adversarial Robustness of Information Bottleneck Models


Jul 12, 2021
Iryna Korshunova, David Stutz, Alexander A. Alemi, Olivia Wiles, Sven Gowal


  Access Paper or Ask Questions

Defending Against Image Corruptions Through Adversarial Augmentations


Apr 20, 2021
Dan A. Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, Andras Gyorgy, Timothy Mann, Sven Gowal


  Access Paper or Ask Questions

Fixing Data Augmentation to Improve Adversarial Robustness


Mar 02, 2021
Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann


  Access Paper or Ask Questions

Verifying Probabilistic Specifications with Functional Lagrangians


Feb 18, 2021
Leonard Berrada, Sumanth Dathathri, Krishnamurthy, Dvijotham, Robert Stanforth, Rudy Bunel, Jonathan Uesato, Sven Gowal, M. Pawan Kumar


  Access Paper or Ask Questions

Autoencoding Variational Autoencoder


Dec 07, 2020
A. Taylan Cemgil, Sumedh Ghaisas, Krishnamurthy Dvijotham, Sven Gowal, Pushmeet Kohli

* Neurips 2020 

  Access Paper or Ask Questions

Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples


Oct 27, 2020
Sven Gowal, Chongli Qin, Jonathan Uesato, Timothy Mann, Pushmeet Kohli


  Access Paper or Ask Questions

An empirical investigation of the challenges of real-world reinforcement learning


Mar 24, 2020
Gabriel Dulac-Arnold, Nir Levine, Daniel J. Mankowitz, Jerry Li, Cosmin Paduraru, Sven Gowal, Todd Hester

* arXiv admin note: text overlap with arXiv:1904.12901 

  Access Paper or Ask Questions

Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations


Dec 06, 2019
Sven Gowal, Chongli Qin, Po-Sen Huang, Taylan Cemgil, Krishnamurthy Dvijotham, Timothy Mann, Pushmeet Kohli


  Access Paper or Ask Questions

Towards Robust Image Classification Using Sequential Attention Models


Dec 04, 2019
Daniel Zoran, Mike Chrzanowski, Po-Sen Huang, Sven Gowal, Alex Mott, Pushmeet Kohl


  Access Paper or Ask Questions

An Alternative Surrogate Loss for PGD-based Adversarial Testing


Oct 21, 2019
Sven Gowal, Jonathan Uesato, Chongli Qin, Po-Sen Huang, Timothy Mann, Pushmeet Kohli


  Access Paper or Ask Questions

Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation


Sep 03, 2019
Po-Sen Huang, Robert Stanforth, Johannes Welbl, Chris Dyer, Dani Yogatama, Sven Gowal, Krishnamurthy Dvijotham, Pushmeet Kohli

* Accepted in EMNLP 2019 

  Access Paper or Ask Questions

Adversarial Robustness through Local Linearization


Jul 04, 2019
Chongli Qin, James Martens, Sven Gowal, Dilip Krishnan, Krishnamurthy, Dvijotham, Alhussein Fawzi, Soham De, Robert Stanforth, Pushmeet Kohli


  Access Paper or Ask Questions

Verification of Non-Linear Specifications for Neural Networks


Feb 25, 2019
Chongli Qin, Krishnamurthy, Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli

* ICLR conference paper 

  Access Paper or Ask Questions

On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models


Nov 05, 2018
Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy Mann, Pushmeet Kohli


  Access Paper or Ask Questions

A Dual Approach to Scalable Verification of Deep Networks


Aug 03, 2018
Krishnamurthy, Dvijotham, Robert Stanforth, Sven Gowal, Timothy Mann, Pushmeet Kohli


  Access Paper or Ask Questions

Learning from Delayed Outcomes with Intermediate Observations


Jul 24, 2018
Timothy A. Mann, Sven Gowal, Ray Jiang, Huiyi Hu, Balaji Lakshminarayanan, Andras Gyorgy


  Access Paper or Ask Questions

Training verified learners with learned verifiers


May 29, 2018
Krishnamurthy Dvijotham, Sven Gowal, Robert Stanforth, Relja Arandjelovic, Brendan O'Donoghue, Jonathan Uesato, Pushmeet Kohli


  Access Paper or Ask Questions

Beyond Greedy Ranking: Slate Optimization via List-CVAE


May 24, 2018
Ray Jiang, Sven Gowal, Timothy A. Mann, Danilo J. Rezende

* Preliminary work. Under review by the Neural Information Processing Systems (NIPS) 2018 

  Access Paper or Ask Questions