Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in 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_ | 1866915597492682752 |
|---|---|
| author | Assumpcao, Nicolas Riccieri Gardin Villas, Leandro |
| author_facet | Assumpcao, Nicolas Riccieri Gardin Villas, Leandro |
| contents | Federated Learning (FL) is a distributed training paradigm wherein participants collaborate to build a global model while ensuring the privacy of the involved data, which remains stored on participant devices. However, proposals aiming to ensure such privacy also make it challenging to protect against potential attackers seeking to compromise the training outcome. In this context, we present Fast, Private, and Protected (FPP), a novel approach that aims to safeguard federated training while enabling secure aggregation to preserve data privacy. This is accomplished by evaluating rounds using participants' assessments and enabling training recovery after an attack. FPP also employs a reputation-based mechanism to mitigate the participation of attackers. We created a dockerized environment to validate the performance of FPP compared to other approaches in the literature (FedAvg, Power-of-Choice, and aggregation via Trimmed Mean and Median). Our experiments demonstrate that FPP achieves a rapid convergence rate and can converge even in the presence of malicious participants performing model poisoning attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning Assumpcao, Nicolas Riccieri Gardin Villas, Leandro Machine Learning Federated Learning (FL) is a distributed training paradigm wherein participants collaborate to build a global model while ensuring the privacy of the involved data, which remains stored on participant devices. However, proposals aiming to ensure such privacy also make it challenging to protect against potential attackers seeking to compromise the training outcome. In this context, we present Fast, Private, and Protected (FPP), a novel approach that aims to safeguard federated training while enabling secure aggregation to preserve data privacy. This is accomplished by evaluating rounds using participants' assessments and enabling training recovery after an attack. FPP also employs a reputation-based mechanism to mitigate the participation of attackers. We created a dockerized environment to validate the performance of FPP compared to other approaches in the literature (FedAvg, Power-of-Choice, and aggregation via Trimmed Mean and Median). Our experiments demonstrate that FPP achieves a rapid convergence rate and can converge even in the presence of malicious participants performing model poisoning attacks. |
| title | Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.02797 |