Publications

The Distillation Game: Adaptive Attacks & Efficient Defenses

Y. Allouah*, M. Haghifam*, S. Koyejo, R. Shokri. (* equal contribution)

FoGen @ ICML 2026 – Workshop on Foundations of Deep Generative Models

paper·code

What to Forget in Unlearning? Forget Set Curation for Language Models

A. Jha, A. Khatua, Y. Allouah, S. Koyejo.

FoGen @ ICML 2026 – Workshop on Foundations of Deep Generative Models

paper·code

Distributional Machine Unlearning via Selective Data Removal

Y. Allouah, R. Guerraoui, S. Koyejo.

ICLR 2026 – International Conference on Learning Representations

MUGen @ ICML 2025 – Workshop on Machine Unlearning for Generative AI (Oral)

paper·code

Certified Unlearning for Neural Networks

A. Koloskova*, Y. Allouah*, A. Jha, R. Guerraoui, S. Koyejo. (* equal contribution)

ICML 2025 – International Conference on Machine Learning

paper·code

Towards Trustworthy Federated Learning with Untrusted Participants

Y. Allouah, R. Guerraoui, J. Stephan.

ICML 2025 – International Conference on Machine Learning

paper

The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning

Y. Allouah, J. Kazdan, R. Guerraoui, S. Koyejo.

ICLR 2025 – International Conference on Learning Representations

paper·slides

Adaptive Gradient Clipping for Robust Federated Learning

Y. Allouah, R. Guerraoui, N. Gupta, A. Jellouli, G. Rizk, J. Stephan.

ICLR 2025 – International Conference on Learning Representations (Spotlight)

paper

Efficient Prediction of Pass@k Scaling in Large Language Models

J. Kazdan, R. Schaeffer, Y. Allouah, C. Sullivan, K. Yu, N. Levi, S. Koyejo.

arXiv 2025 – Preprint

paper

The Privacy Power of Correlated Noise in Decentralized Learning

Y. Allouah, A. Koloskova, A. El Firdoussi, M. Jaggi, R. Guerraoui.

ICML 2024 – International Conference on Machine Learning

paper·code

Robust Sparse Voting

Y. Allouah, R. Guerraoui, L. Hoang, O. Villemaud.

AISTATS 2024 – International Conference on Artificial Intelligence and Statistics

paper·code

Revisiting Ensembling in One-Shot Federated Learning

Y. Allouah, A. Dhasade, R. Guerraoui, N. Gupta, A.-M. Kermarrec, R. Pinot, R. Pires, R. Sharma.

NeurIPS 2024 – Conference on Neural Information Processing Systems

paper

Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients

Y. Allouah, A. El Mrini, R. Guerraoui, N. Gupta, R. Pinot.

NeurIPS 2024 – Conference on Neural Information Processing Systems

paper

Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates

Y. Allouah, S. Farhadkhani, R. Guerraoui, N. Gupta, R. Pinot, G. Rizk, S. Voitovych.

ICML 2024 – International Conference on Machine Learning

paper

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

Y. Allouah, R. Guerraoui, N. Gupta, R. Pinot, G. Rizk.

NeurIPS 2023 – Conference on Neural Information Processing Systems (Spotlight)

paper·code·video

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Y. Allouah, R. Guerraoui, N. Gupta, R. Pinot, J. Stephan.

ICML 2023 – International Conference on Machine Learning

paper·video

Fixing by Mixing: a Recipe for Optimal Byzantine ML under Heterogeneity

Y. Allouah, S. Farhadkhani, R. Guerraoui, N. Gupta, R. Pinot, J. Stephan.

AISTATS 2023 – International Conference on Artificial Intelligence and Statistics

paper

Further Results on Latent Discourse Models and Word Embeddings

S. Khalife, D. Goncalves, Y. Allouah, L. Liberti.

JMLR 2021 – Journal of Machine Learning Research

paper

The Cost of Trust in Machine Learning: Privacy, Robustness, Unlearning, and their Interactions

Y. Allouah.

EPFL 2025 – Doctoral thesis

thesis