Posts by Collection

news

Portfolio item number 2

Short description of portfolio item number 2

publications

Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets

Published in NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications, 2022, 2022

An extension of mixup in the frequency domain that regularizes the deep nets for robustness to common corruptions.

Recommended citation: Ngnawe, J., NJIFON, M. A., Heek, J., and Dauphin, Y. Robustmix: Improving robustness by regularizing the frequency bias of deep nets. In NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications, 2022. URL https://openreview.net/forum?id=Na64z0YpOx.
Download Paper | Download Slides

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers.

Published in Neurips 2024, 2024

A novel property of deep robust classifiers that allows to use the logit margin as a proxy score for input margin and efficiently detect non-robust samples, vulnerable to adversarial attacks.

Recommended citation: Ngnawé, J., Sahoo, S., Pequignot, Y., Precioso, F., & Gagné, C. (2024). Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers. The Thirty-eighth Annual Conference on Neural Information Processing Systems.
Download Paper | Download Slides

A Layer Selection Approach to Test Time Adaptation

Published in AAAI 2025, 2025

A gradient alignement method for layer selection in Test Time Adaptation.

Recommended citation: Sahoo, S., ElAraby, M., Ngnawe, J., Pequignot, Y. B., Precioso, F., & Gagné, C. (2025, April). A layer selection approach to test time adaptation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 19, pp. 20237-20245).
Download Paper | Download Slides

A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy

Published in NeurIPS 2025 Reliable ML Workshop, 2025

This work presents the most comprehensive benchmark of robust fine-tuning to date, revealing how architecture, pretraining, and adaptation choices impact robust generalization across diverse datasets, perturbations, and training protocols.

Recommended citation: Heuillet, M., Bhagwatkar, R., Ngnawé. J., Pequignot, Y., Larouche, A., Gagné, C., Rish, I., Ahmad, O., Durand, A. (2025). A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy. arXiv preprint arXiv:2508.14079.
Download Paper | Download Slides

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling

Published in NeurIPS 2025 Reliable ML Workshop, 2025

We study robust fine-tuning (RFT) of non-robust pretrained models and show that robust objectives cause suboptimal transfer. We propose Epsilon-Scheduling, which enables optimal transfer and improves expected robustness.

Recommended citation: Ngnawé. J., Heuillet, M., Sahoo, S., Pequignot, Ahmad, O., Durand, A. Y., Precioso, F., Gagné, C. (2025). Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling. arXiv preprint arXiv:2509.23325.
Download Paper | Download Slides