Sven Gowal
Publications by Year
Research Areas
Adversarial Robustness in Machine Learning, Anomaly Detection Techniques and Applications, Advanced Neural Network Applications, Reinforcement Learning in Robotics, Explainable Artificial Intelligence (XAI)
Most-Cited Works
- → Challenges of real-world reinforcement learning: definitions, benchmarks and analysis(2021)542 cited
- → On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models(2018)300 cited
- → A Dual Approach to Scalable Verification of Deep Networks(2018)172 cited
- → Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples(2020)144 cited
- → Scalable Verified Training for Provably Robust Image Classification(2019)137 cited
- Adversarial Robustness through Local Linearization(2019)
- → Towards Stable and Efficient Training of Verifiably Robust Neural\n Networks(2019)128 cited
- → Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation(2019)122 cited
- → Fixing Data Augmentation to Improve Adversarial Robustness(2021)104 cited
- → Generative models improve fairness of medical classifiers under distribution shifts(2024)103 cited