5 citations · 9 across the 18 of their papers we have counts for
19 papers
How Reusable Are Benchmarks with Richer Feedback?
Youssef Allouah, John Duchi
We study whether benchmarks reliably guide model selection as developers adapt to evaluation feedback across multiple criteria. We find that the worst-case test-set size needed to…
What to Forget in Unlearning? Forget Set Curation for Language Models
Animesh Jha, Arpandeep Khatua, Youssef Allouah +1
Machine unlearning aims to remove targeted data or behaviors from a trained model without retraining from scratch. Yet most evaluations assume that the examples to forget are alrea…
The Distillation Game: Adaptive Evaluations & Efficient Defenses
Youssef Allouah, Mahdi Haghifam, Sanmi Koyejo +1
Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate. We study this trade-off t…
Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding
Chengxi Li, Youssef Allouah, Rachid Guerraoui +2
In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication constraints. While prior work has developed various robust aggregation r…
Efficient Prediction of Pass@k Scaling in Large Language Models
Joshua Kazdan, Rylan Schaeffer, Youssef Allouah +4
Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase b…
Distributional Machine Unlearning via Selective Data Removal
Youssef Allouah, Rachid Guerraoui, Sanmi Koyejo
Machine learning systems increasingly face requirements to remove entire domains of information--such as toxic language or biases--rather than individual user data. This task prese…
Certified Unlearning for Neural Networks
Anastasia Koloskova, Youssef Allouah, Animesh Jha +2
We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regul…
Towards Trustworthy Federated Learning with Untrusted Participants
Youssef Allouah, Rachid Guerraoui, John Stephan
Resilience against malicious participants and data privacy are essential for trustworthy federated learning, yet achieving both with good utility typically requires the strong assu…
The Utility and Complexity of in- and out-of-Distribution Machine Unlearning
Youssef Allouah, Joshua Kazdan, Rachid Guerraoui +1
Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment. Despit…
Revisiting Ensembling in One-Shot Federated Learning
Youssef Allouah, Akash Dhasade, Rachid Guerraoui +5
Federated learning (FL) is an appealing approach to training machine learning models without sharing raw data. However, standard FL algorithms are iterative and thus induce a signi…
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
Youssef Allouah, Abdellah El Mrini, Rachid Guerraoui +2
Federated learning (FL) is an appealing paradigm that allows a group of machines (a.k.a. clients) to learn collectively while keeping their data local. However, due to the heteroge…
The Privacy Power of Correlated Noise in Decentralized Learning
Youssef Allouah, Anastasia Koloskova, Aymane El Firdoussi +2
Decentralized learning is appealing as it enables the scalable usage of large amounts of distributed data and resources (without resorting to any central entity), while promoting p…
Adaptive Gradient Clipping for Robust Federated Learning
Youssef Allouah, Rachid Guerraoui, Nirupam Gupta +3
Robust federated learning aims to maintain reliable performance despite the presence of adversarial or misbehaving workers. While state-of-the-art (SOTA) robust distributed gradien…
Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
Youssef Allouah, Sadegh Farhadkhani, Rachid GuerraouI +4
The possibility of adversarial (a.k.a., {\em Byzantine}) clients makes federated learning (FL) prone to arbitrary manipulation. The natural approach to robustify FL against adversa…
Balancing Privacy, Robustness, and Efficiency in Machine Learning
Youssef Allouah, Rachid Guerraoui, John Stephan
This position paper argues that achieving robustness, privacy, and efficiency simultaneously in machine learning systems is infeasible under prevailing threat models. The tension b…
Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity
Youssef Allouah, Rachid Guerraoui, Nirupam Gupta +2
The theory underlying robust distributed learning algorithms, designed to resist adversarial machines, matches empirical observations when data is homogeneous. Under data heterogen…
Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity
Youssef Allouah, Sadegh Farhadkhani, Rachid Guerraoui +3
Byzantine machine learning (ML) aims to ensure the resilience of distributed learning algorithms to misbehaving (or Byzantine) machines. Although this problem received significant…
On the Privacy-Robustness-Utility Trilemma in Distributed Learning
Youssef Allouah, Rachid Guerraoui, Nirupam Gupta +2
The ubiquity of distributed machine learning (ML) in sensitive public domain applications calls for algorithms that protect data privacy, while being robust to faults and adversari…
Robust Sparse Voting
Youssef Allouah, Rachid Guerraoui, Lê-Nguyên Hoang +1
Many applications, such as content moderation and recommendation, require reviewing and scoring a large number of alternatives. Doing so robustly is however very challenging. Indee…