Sommaire

  • Cet exposé a été présenté le 25 mars 2022.

Description

  • Orateur

    Dario Pasquini (EPFL)

This talk is about inaccurate assumptions, unrealistic trust models, and flawed methodologies affecting current collaborative machine learning techniques. In the presentation, we cover different security issues concerning both emerging approaches and well-established solutions in privacy-preserving collaborative machine learning. We start by discussing the inherent insecurity of Split Learning and peer-to-peer collaborative learning. Then, we talk about the soundness of current Secure Aggregation protocols in Federated Learning, showing that those do not provide any additional level of privacy to users. Ultimately, the objective of this talk is to highlight the general errors and flawed approaches we all should avoid in devising and implementing "privacy-preserving collaborative machine learning".

Infos pratiques

Prochains exposés

  • Users Pay Twice: The Hidden Energy Cost of Web Advertising

    • 04 décembre 2026 (11:00 - 12:00)

    • Inria Center of the University of Rennes - Room Petri/Turing

    Orateur : Samuel Pélissier - CentraleSupélec

    Advertisements are everywhere on the Web: search engines promote results, most websites display ads, some require users to accept ads as a condition for access, video streaming services fund their infrastructure through an increasing volume of ads, and much of the gaming industry has adopted ad-based revenue models. In exchange for free access to a wide range of content, web users sacrifice their[…]
    • Privacy

Voir les exposés passés