Sven Gowal

发表

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

Timothy A. Mann, Jonathan Uesato, Pushmeet Kohli, 2018, ArXiv.

Fixing Data Augmentation to Improve Adversarial Robustness pdf

Timothy A. Mann, Sven Gowal, Olivia Wiles, 2021, ArXiv.

VERIFIABLY ROBUST NEURAL NETWORKS

Cho-Jui Hsieh, Sven Gowal, Robert Stanforth, 2019 .

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

Timothy A. Mann, Jonathan Uesato, Pushmeet Kohli, 2020, ArXiv.

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

D. Mankowitz, Cosmin Paduraru, Todd Hester, 2020, ArXiv.

Robustness of Epinets against Distributional Shifts

Benjamin Van Roy, Ian Osband, Sven Gowal, 2022, ArXiv.

Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning

Sven Gowal, Olivia Wiles, Isabela Albuquerque, 2022, ArXiv.

Evaluating the Adversarial Robustness of Adaptive Test-time Defenses

Evan Shelhamer, Matthias Hein, A. Cemgil, 2022, ICML.

Scalable Neural Learning for Verifiable Consistency with Temporal Specifications

Ramana Kumar, Po-Sen Huang, Pushmeet Kohli, 2019 .

Revisiting adapters with adversarial training

Sven Gowal, Francesco Croce, Sylvestre-Alvise Rebuffi, 2022, ICLR.

Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation

Dani Yogatama, Pushmeet Kohli, Krishnamurthy Dvijotham, 2019, EMNLP.

Self-supervised Adversarial Robustness for the Low-label, High-data Regime

Pushmeet Kohli, Sven Gowal, Aäron van den Oord, 2021, ICLR.

Pipeline To Generate Training Data For Image Recognition

Sven Gowal, Rahul Garg, Sven Gowal, 2015 .

Challenges of real-world reinforcement learning: definitions, benchmarks and analysis

Nir Levine, Gabriel Dulac-Arnold, Sven Gowal, 2021, Machine Learning.

Defending Against Image Corruptions Through Adversarial Augmentations pdf

Timothy A. Mann, Sven Gowal, Olivia Wiles, 2021, ICLR.

Data Augmentation Can Improve Robustness pdf

Sven Gowal, Timothy Mann, Olivia Wiles, 2021, NeurIPS.

Improving Robustness using Generated Data pdf

Sven Gowal, Dan Andrei Calian, Timothy Mann, 2021, NeurIPS.

Fixing Data Augmentation to Improve Adversarial Robustness

Timothy A. Mann, Florian Stimberg, Sven Gowal, 2021, ArXiv.

A Dual Approach to Verify and Train Deep Networks

Pushmeet Kohli, Timothy A. Mann, Sven Gowal, 2019, IJCAI.

Competition-level code generation with AlphaCode

Cherepanov, Xinyun Chen, Oriol Vinyals, 2022, Science.

A Dual Approach to Scalable Verification of Deep Networks

Pushmeet Kohli, Timothy A. Mann, Sven Gowal, 2018, UAI.

Adversarial Robustness through Local Linearization

Pushmeet Kohli, Sven Gowal, Krishnamurthy Dvijotham, 2019, NeurIPS.

A Fine-Grained Analysis on Distribution Shift pdf

Ali Taylan Cemgil, Sven Gowal, Krishnamurthy Dvijotham, 2021, ICLR.

Beyond Greedy Ranking: Slate Optimization via List-CVAE

Timothy A. Mann, Sven Gowal, Danilo Jimenez Rezende, 2018, ICLR.

Efficient Neural Network Verification with Exactness Characterization

Pushmeet Kohli, Sven Gowal, Krishnamurthy Dvijotham, 2019, UAI.

A Framework for robustness Certification of Smoothed Classifiers using F-Divergences

Pushmeet Kohli, Borja Balle, Sven Gowal, 2020, ICLR.

Generative models improve fairness of medical classifiers under distribution shifts

Abhijit Guha Roy, Pushmeet Kohli, A. Cemgil, 2023, Nature medicine.

Differentially Private Diffusion Models Generate Useful Synthetic Images

Samuel L. Smith, Sven Gowal, Robert Stanforth, 2023, ArXiv.

Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning

Sven Gowal, Olivia Wiles, Isabela Albuquerque, 2022, ArXiv.

An Alternative Surrogate Loss for PGD-based Adversarial Testing pdf

Po-Sen Huang, Pushmeet Kohli, Timothy A. Mann, 2019, ArXiv.

Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications

Sumanth Dathathri, Sven Gowal, Krishnamurthy Dvijotham, 2021, NeurIPS.

Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations

Timothy A. Mann, Pushmeet Kohli, Krishnamurthy Dvijotham, 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Scalable Verified Training for Provably Robust Image Classification

Sven Gowal, Robert Stanforth, Sven Gowal, 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

The Autoencoding Variational Autoencoder pdf

Pushmeet Kohli, Sven Gowal, Sumedh Ghaisas, 2020, NeurIPS.

Towards Robust Image Classification Using Sequential Attention Models

Po-Sen Huang, Pushmeet Kohli, Alex Mott, 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts

Evan Shelhamer, Sven Gowal, Francesco Croce, 2023, arXiv.org.

S ELF-SUPERVISED A DVERSARIAL R OBUSTNESS FOR THE L OW-LABEL , H IGH-DATA R EGIME

Aäron van den Oord, Pushmeet Kohli, Po-Sen Huang, 2021 .

Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control

Pushmeet Kohli, Sven Gowal, Krishnamurthy Dvijotham, 2020, ICLR.

Hindering Adversarial Attacks with Implicit Neural Representations

Andrei A. Rusu, R. Hadsell, Sven Gowal, 2022, ICML.

Training verified learners with learned verifiers pdf

Pushmeet Kohli, Sven Gowal, Krishnamurthy Dvijotham, 2018, ArXiv.

Verification of Non-Linear Specifications for Neural Networks pdf

Pushmeet Kohli, Sven Gowal, Krishnamurthy Dvijotham, 2019, ICLR.

Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems

András György, Timothy A. Mann, Sven Gowal, 2018, ICML.

A realistic simulator for the design and evaluation of intelligent vehicles

Yizhen Zhang, Alcherio Martinoli, Sven Gowal, 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

Benchmarking Robustness to Adversarial Image Obfuscations

Cyrus Rashtchian, Florian Stimberg, Sven Gowal, 2023, NeurIPS.