On the Privacy-Robustness-Utility Trilemma in Distributed Learning
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...
In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...
Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...
A multi-agent system consists of a collection of decision-making or learning agents subjected to streaming observations from some real-world phenomenon. The goal of the system is to solve some global learning or optimization problem in a distributed or dec ...
As modern machine learning continues to achieve unprecedented benchmarks, the resource demands to train these advanced models grow drastically. This has led to a paradigm shift towards distributed training. However, the presence of adversariesâwhether ma ...
Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data (e.g., adding Ga ...
Predictive models based on machine learning (ML) offer a compelling promise: bringing clarity and structure to complex natural and social environments. However, the use of ML poses substantial risks related to the privacy of their training data as well as ...
We consider the problem of enhancing user privacy in common data analysis and machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples from a generative adversarial network. We propose employing ...
In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning-a collaborative machine learning framework aimed at addressing the main limitations of federated learning. We introduce a suite of novel attacks for both passive and ...
The problem of Byzantine resilience in distributed machine learning, a.k.a., Byzantine machine learning, consists in designing distributed algorithms that can train an accurate model despite the presence of Byzantine nodes, i.e., nodes with corrupt data or ...
