Publications
2024
- TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
Thibault Simonetto, Salah Ghamizi and Maxime Cordy.
In Advances in Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS), 2024. - Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
Thibault Simonetto, Salah Ghamizi and Maxime Cordy.
In Advances in Neural Information Processing Systems (NeurIPS), 2024. - On the Impact of Industrial Delays when Mitigating Distribution Drifts: an Empirical Study on Real-world Financial Systems
Thibault Simonetto, Salah Ghamizi, Maxime Cordy, Yves Le Traon, Clément Lefebvre, Andrey Boystov and Anne Goujon.
In KDD 2024 Discovering Drift Phenomena in Evolving Landscape Workshop, 2024.Studies the impact of industrial delays on mitigating distribution drifts in financial systems.
- Towards Adaptive Attacks on Constrained Tabular Machine Learning
Thibault Simonetto, Salah Ghamizi and Maxime Cordy.
In ICML 2024 Next Generation of AI Safety Workshop, 2024.
2023
- On the Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks
Salijona Dyrmishi, Salah Ghamizi, Thibault Simonetto, Yves Le Traon and Maxime Cordy.
In Proceedings of the 2023 IEEE Symposium on Security and Privacy (SP), 2023.
2022
- A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space
Thibault Simonetto, Salijona Dyrmishi, Salah Ghamizi, Maxime Cordy and Yves Le Traon.
In Thirty-First International Joint Conference on Artificial Intelligence (IJCAI), 2022.