50 citations · 76 across the 10 of their papers we have counts for
12 papers
No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning
Francesco Diana, Chuan Xu, André Nusser +1
Gradient inversion attacks threaten client privacy in federated learning by reconstructing training samples from clients' shared gradients. Gradients aggregate contributions from m…
Deadline-Aware Online Scheduling for LLM Fine-Tuning with Spot Market Predictions
Linggao Kong, Yuedong Xu, Lei Jiao +1
As foundation models grow in size, fine-tuning them becomes increasingly expensive. While GPU spot instances offer a low-cost alternative to on-demand resources, their volatile pri…
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
Diksha Gupta, Antonio Honsell, Chuan Xu +2
Distributed learning enables scalable model training over decentralized data, but remains hindered by Byzantine faults and high communication costs. While both challenges have been…
Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learning
Francesco Diana, André Nusser, Chuan Xu +1
Federated Learning (FL) enables collaborative training of machine learning models across distributed clients without sharing raw data, ostensibly preserving data privacy. Neverthel…
Attribute Inference Attacks for Federated Regression Tasks
Francesco Diana, Othmane Marfoq, Chuan Xu +3
Federated Learning (FL) enables multiple clients, such as mobile phones and IoT devices, to collaboratively train a global machine learning model while keeping their data localized…
Federated Learning for Collaborative Inference Systems: The Case of Early Exit Networks
Caelin Kaplan, Angelo Rodio, Tareq Si Salem +2
As Internet of Things (IoT) technology advances, end devices like sensors and smartphones are progressively equipped with AI models tailored to their local memory and computational…
A Cautionary Tale: On the Role of Reference Data in Empirical Privacy Defenses
Caelin G. Kaplan, Chuan Xu, Othmane Marfoq +2
Within the realm of privacy-preserving machine learning, empirical privacy defenses have been proposed as a solution to achieve satisfactory levels of training data privacy without…
Local Model Reconstruction Attacks in Federated Learning and their Uses
Ilias Driouich, Chuan Xu, Giovanni Neglia +2
In this paper, we initiate the study of local model reconstruction attacks for federated learning, where a honest-but-curious adversary eavesdrops the messages exchanged between a…
Efficient passive membership inference attack in federated learning
Oualid Zari, Chuan Xu, Giovanni Neglia
In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally. H…
Throughput-Optimal Topology Design for Cross-Silo Federated Learning
Othmane Marfoq, Chuan Xu, Giovanni Neglia +1
Federated learning usually employs a client-server architecture where an orchestrator iteratively aggregates model updates from remote clients and pushes them back a refined model.…
Dynamic backup workers for parallel machine learning
Chuan Xu, Giovanni Neglia, Nicola Sebastianelli
The most popular framework for distributed training of machine learning models is the (synchronous) parameter server (PS). This paradigm consists of workers, which iteratively…
Decentralized gradient methods: does topology matter?
Giovanni Neglia, Chuan Xu, Don Towsley +1
Consensus-based distributed optimization methods have recently been advocated as alternatives to parameter server and ring all-reduce paradigms for large scale training of machine…