13 papers
Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning
Ousmane Touat, César Sabater, Mohamed Maouche +1
Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clients train a machine l…
GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework
Yacine Belal, Mohamed Maouche, Sonia Ben Mokhtar
Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers. Recent approaches rely on dyn…
On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
Johan Erbani, Pierre-Edouard Portier, Elod Egyed-Zsigmond +2
The confusion matrix is a standard tool for evaluating classifiers by providing insights into class-level errors. In heterogeneous settings, its values are shaped by two main facto…
DOME: Improving Signal-to-Noise in Stochastic Gradient Descent via Sharp-Direction Subspace Filtering
Julien Nicolas, Mohamed Maouche, Sonia Ben Mokhtar +1
Stochastic gradients for deep neural networks exhibit strong correlations along the optimization trajectory, and are often aligned with a small set of Hessian eigenvectors associat…
TriHaRd: Higher Resilience for TEE Trusted Time
Matthieu Bettinger, Sonia Ben Mokhtar, Pascal Felber +3
Accurately measuring time passing is critical for many applications. However, in Trusted Execution Environments (TEEs) such as Intel SGX, the time source is outside the Trusted Com…
A Weighted Loss Approach to Robust Federated Learning under Data Heterogeneity
Johan Erbani, Sonia Ben Mokhtar, Pierre-Edouard Portier +2
Federated learning (FL) is a machine learning paradigm that enables multiple data holders to collaboratively train a machine learning model without sharing their training data with…