Youssef Allouah

I am a postdoctoral researcher at Stanford University. I received my PhD in Computer Science from EPFL and graduated in Mathematics and Computer Science from Ecole Polytechnique. I also interned at Amazon.

My research develops foundations and methods for trustworthy machine learning, spanning privacy, robustness, and machine unlearning.

Youssef Allouah

Recent Publications

See the publications page for the complete list.

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

papercode

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

papercode

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)

papercode

Certified Unlearning for Neural Networks

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

ICML 2025 – International Conference on Machine Learning

papercode