| Download | - View accepted manuscript: An alternative approach to federated learning for model security and data privacy (PDF, 570 KiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.5220/0013237500003899 |
|---|
| Author | Search for: Briguglio, WilliamORCID identifier: https://orcid.org/0000-0002-2357-3966; Search for: Yousef, WaleedORCID identifier: https://orcid.org/0000-0001-9669-7241; Search for: Traoré, IssaORCID identifier: https://orcid.org/0000-0003-2987-8047; Search for: Mamun, Mohammad1ORCID identifier: https://orcid.org/0000-0002-4045-8687; Search for: Saad, SherifORCID identifier: https://orcid.org/0000-0002-5506-5261 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 11th International Conference on Information Systems Security and Privacy, February 20-22, 2025, Porto, Portugal |
|---|
| Subject | data poisoning; federated learning; model poisoning; non-IID |
|---|
| Abstract | Federated learning (FL) enables machine learning on data held across multiple clients without exchanging private data. However, exchanging information for model training can compromise data privacy. Further, participants may be untrustworthy and can attempt to sabotage model performance. Also, data that is not independently and identically distributed (IID) impede the convergence of FL techniques. We present a general framework for federated learning via aggregating multivariate estimated densities (FLAMED). FLAMED aggregates density estimations of clients’ data, from which it simulates training datasets to perform centralized learning, bypassing problems arising from non-IID data and contributing to addressing privacy and security concerns. FLAMED does not require a copy of the global model to be distributed to each participant during training, meaning the aggregating server can retain sole proprietorship of the global model without the use of resource-intensive homomorphic encrypti on. We compared its performance to standard FL approaches using synthetic and real datasets and evaluated its resilience to model poisoning attacks. Our results indicate that FLAMED effectively handles non-IID data in many settings while also being more secure. |
|---|
| Publication date | 2025 |
|---|
| Publisher | SCITEPRESS - Science and Technology Publications |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 96f2e1e2-a1f9-4247-8497-7ab80a91fe20 |
|---|
| Record created | 2025-03-12 |
|---|
| Record modified | 2025-03-14 |
|---|
