Stake-Driven Rewards and Log-Based Free Rider Detection in Federated Learning
Nguyen, Huong; Nguyen, Hong-Tri; Lovén, Lauri; Pirttikangas, Susanna (2024-12-16)
IEEE
16.12.2024
H. Nguyen, H. -T. Nguyen, L. Lovén and S. Pirttikangas, "Stake-Driven Rewards and Log-Based Free Rider Detection in Federated Learning," 2024 21st Annual International Conference on Privacy, Security and Trust (PST), Sydney, Australia, 2024, pp. 1-10, doi: 10.1109/PST62714.2024.10788055
https://rightsstatements.org/vocab/InC/1.0/
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists,or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists,or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202502101543
https://urn.fi/URN:NBN:fi:oulu-202502101543
Tiivistelmä
Abstract
Federated learning has become increasingly popular due to its ability to bring together multiple learners, enhance model generalizability, and promote knowledge exchange. Such systems inherently rely on the bedrock of security, trust, and fairness among training workers to ensure a conducive learning environment. However, this collaborative landscape has encoun-tered the challenge of free riders, individuals who join the systems to gain benefits without making any substantial contributions. This can negatively impact learning outcomes, fairness, sustain-ability, and trust in a collaborative system. In this paper, we first present a novel stake-based incentive mechanism aimed at promoting active participation among contributors, and con-currently maximizing the reward for clients with consideration of free rider presence in the system. Second, we propose an efficient method for identifying free riders in federated learning based on log analysis. Our method delegates the detection of free riders to training workers and the identification to the aggregator, rather than relying solely on the aggregator. We simulate potential deceptive strategies employed by free riders and assess the extent of our method's coverage across these scenarios. The experimental results conducted on different free rider ratios demonstrate the versatility and applicability of our approach in detecting these clients within the federated learning paradigm.
Federated learning has become increasingly popular due to its ability to bring together multiple learners, enhance model generalizability, and promote knowledge exchange. Such systems inherently rely on the bedrock of security, trust, and fairness among training workers to ensure a conducive learning environment. However, this collaborative landscape has encoun-tered the challenge of free riders, individuals who join the systems to gain benefits without making any substantial contributions. This can negatively impact learning outcomes, fairness, sustain-ability, and trust in a collaborative system. In this paper, we first present a novel stake-based incentive mechanism aimed at promoting active participation among contributors, and con-currently maximizing the reward for clients with consideration of free rider presence in the system. Second, we propose an efficient method for identifying free riders in federated learning based on log analysis. Our method delegates the detection of free riders to training workers and the identification to the aggregator, rather than relying solely on the aggregator. We simulate potential deceptive strategies employed by free riders and assess the extent of our method's coverage across these scenarios. The experimental results conducted on different free rider ratios demonstrate the versatility and applicability of our approach in detecting these clients within the federated learning paradigm.
Kokoelmat
- Avoin saatavuus [38823]