EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

2010. Machine Learning in Untrusted Distributed Environment

Invited abstract in session WD-32: Distributed and Federated Optimization, stream Advances in large scale nonlinear optimization.

Wednesday, 14:30-16:00
Room: 41 (building: 303A)

Authors (first author is the speaker)

1. Nirupam Gupta
Computer Science, EPFL

Abstract

Machine learning algorithms, where the computing system learns from data in order to adjust its behavior, are the key enabler of modern AI-based technologies. This dependency on data, however, is also the Achille's heel of AI systems. The data, which can come from a wide variety of sources, is not always trustworthy. Some sources can provide erroneous or corrupted data. With current machine learning algorithms, a single "bad" source can lead the entire learning scheme to make critical mistakes. Moreover, to handle the huge amounts of data, machine learning algorithms are often deployed over a large network of machines. Consequently, as the network size increases, the likelihood of machine errors also increases. Indeed, software and hardware bugs are prevalent, and machines can sometimes be hacked by malicious players. Some of these players attempt to corrupt the entire learning procedure, merely for the pleasure of claiming to have destroyed an important system. Others attempt to influence the learning procedure for their own benefit.

Building distributed machine learning schemes that are robust to these events is paramount to transitioning AI from being a mere spectacle capable of momentary feats to a dependable tool with guaranteed safety. In this talk, I will cover some effective techniques for achieving such robustness. Specifically, I will present distributed machine learning algorithms that do not trust any individual data source or computing unit.

Keywords

Status: accepted


Back to the list of papers