Researchers from the AI4EOSC project presented a paper entitled “Making Federated Learning Accessible to Scientists: The AI4EOSC Approach” during the 12th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec), one of the prime events in the area of multimedia security, held in Baiona, Spain, on June 24-26, 2024.
The presentation delved on the implementation of a federated learning system based on the Flower framework that allows users to exploit this technique within the AI4EOSC platform, together with the difficulties encountered in the process and how they have been solved. Besides, it explored different additional extensions developed (available for use on the platform, such as client authentication), as well as an example applied to a medical imaging case, concluding with an scenario of intermittent clients in medical imaging.
The paper, authored by researchers from CSIC, IISAS and KIT, and presented by CSIC’s Judith Sáinz-Pardo, can be consulted in open access in the conference proceedings, which are now available.
The AI4EOSC paper presentation was part of the special session on Security and Privacy Challenges towards Trustworthy Federated Learning, one of the seven sessions held: (1) Steganography & Steganalysis, (2) Special Session on Reliable Detectors in Multimedia Forensics and Steganalysis, (3) Special Session on Stego-Malware: Attribution, Analysis and Detection, (4) Forensics, (5) Challenges in Multimedia Security, (6) Special Session on Security and Privacy Challenges towards Trustworthy Federated Learning and (7) Special Session on Unveiling Trends and Challenges in Audio Deepfake Detection. The event ended on the afternoon of Wednesday June 26 with a roundtable on Challenges in Multimedia Forensics and Steganalysis in relation to AI.
Since 2013, IH&MMSec unite two long-standing workshop series: The Information Hiding Workshop (IH), and the ACM Workshop on Multimedia and Security (MM&Sec). As stated in this past edition webpage: “The research presented at this workshop captures state-of-the-art work conducted in academic, industrial, and government institutions worldwide”.
