Towards Trustworthy Federated Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929742937063424 |
|---|---|
| author | Basharat, Alina Bian, Yijun Xu, Ping Tian, Zhi |
| author_facet | Basharat, Alina Bian, Yijun Xu, Ping Tian, Zhi |
| contents | This paper develops a comprehensive framework to address three critical trustworthy challenges in federated learning (FL): robustness against Byzantine attacks, fairness, and privacy preservation. To improve the system's defense against Byzantine attacks that send malicious information to bias the system's performance, we develop a Two-sided Norm Based Screening (TNBS) mechanism, which allows the central server to crop the gradients that have the l lowest norms and h highest norms. TNBS functions as a screening tool to filter out potential malicious participants whose gradients are far from the honest ones. To promote egalitarian fairness, we adopt the q-fair federated learning (q-FFL). Furthermore, we adopt a differential privacy-based scheme to prevent raw data at local clients from being inferred by curious parties. Convergence guarantees are provided for the proposed framework under different scenarios. Experimental results on real datasets demonstrate that the proposed framework effectively improves robustness and fairness while managing the trade-off between privacy and accuracy. This work appears to be the first study that experimentally and theoretically addresses fairness, privacy, and robustness in trustworthy FL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03684 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Trustworthy Federated Learning Basharat, Alina Bian, Yijun Xu, Ping Tian, Zhi Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing This paper develops a comprehensive framework to address three critical trustworthy challenges in federated learning (FL): robustness against Byzantine attacks, fairness, and privacy preservation. To improve the system's defense against Byzantine attacks that send malicious information to bias the system's performance, we develop a Two-sided Norm Based Screening (TNBS) mechanism, which allows the central server to crop the gradients that have the l lowest norms and h highest norms. TNBS functions as a screening tool to filter out potential malicious participants whose gradients are far from the honest ones. To promote egalitarian fairness, we adopt the q-fair federated learning (q-FFL). Furthermore, we adopt a differential privacy-based scheme to prevent raw data at local clients from being inferred by curious parties. Convergence guarantees are provided for the proposed framework under different scenarios. Experimental results on real datasets demonstrate that the proposed framework effectively improves robustness and fairness while managing the trade-off between privacy and accuracy. This work appears to be the first study that experimentally and theoretically addresses fairness, privacy, and robustness in trustworthy FL. |
| title | Towards Trustworthy Federated Learning |
| topic | Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2503.03684 |