Abstract

The emergence of the Fediverse, an ecosystem of interconnected, decentralised online social networks makes content moderation more challenging and urgent. Key to the success of the Fediverse is the ability to freely deploy and interconnect across a variety of online social networks. The Fediverse is composed of independently hosted but interconnected servers that implement alternatives (e.g., PeerTube, Pixefeld or Owncast) to centralised services (e.g., Youtube, Instagram and Owncast). While this decentralised approach has the benefit of greater privacy, it u ndermines efforts that rely on large data pools like content moderation. Privacy-preserving federated machine learning offers an opportunity to embrace the benefits of this decentralised approach while optimising the training of the required algorithms. I will first show the scale of the challenge and then demonstrate how decentralised moderation can be a successful approach for data-intensive challenges in a privacy-preserving distributed ecosystem.

Bio
Ignacio Castro is Lecturer in Data Analytics at Queen Mary University of London. He obtained his PhD while researching at the Institute IMDEA Networks (Madrid, Spain), and visiting UC Berkeley (California, USA). His work sits at the intersection between economics and computer systems. His interest spans from online social networks and moderation to the macroscopic evolution of the Internet. He has been an investigator on three major EPSRC grants that hold over £6 million in funding. His work appears in top tier journals and conferences including Web Conference, ACM SIGMETRICS, ACM IMC, and IEEE/ACM Trans. on Networking. He also serves in TPCs and organises top tier conferences including IMC, CoNEXT and SIGCOMM.