File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TPSISA52974.2021.00052
- Scopus: eid_2-s2.0-85128765442
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: The TSC-PFed Architecture for Privacy-Preserving FL
Title | The TSC-PFed Architecture for Privacy-Preserving FL |
---|---|
Authors | |
Keywords | federated-learning machine-learning privacy privacy-preserving-machine-learning security trust |
Issue Date | 2021 |
Citation | Proceedings - 2021 3rd IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications, TPS-ISA 2021, 2021, p. 207-216 How to Cite? |
Abstract | In this paper we will introduce our system for trust and security enhanced customizable private federated learning: TSC-PFed. We combine secure multiparty computation and differential privacy to allow participants to leverage known trust dynamics which allow for increased ML model accuracy while preserving privacy guarantees and introduce an update auditor to protect against malicious participants launching dangerous label flipping data poisoning. We additionally introduce customizable modules into the TSC-PFed ecosystem which (a) allow users to customize the type of privacy protection provided and (b) provide a tiered participant selection approach which considers variation in privacy budgets. |
Persistent Identifier | http://hdl.handle.net/10722/343369 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Truex, Stacey | - |
dc.contributor.author | Liu, Ling | - |
dc.contributor.author | Gursoy, Mehmet Emre | - |
dc.contributor.author | Wei, Wenqi | - |
dc.contributor.author | Chow, Ka Ho | - |
dc.date.accessioned | 2024-05-10T09:07:33Z | - |
dc.date.available | 2024-05-10T09:07:33Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings - 2021 3rd IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications, TPS-ISA 2021, 2021, p. 207-216 | - |
dc.identifier.uri | http://hdl.handle.net/10722/343369 | - |
dc.description.abstract | In this paper we will introduce our system for trust and security enhanced customizable private federated learning: TSC-PFed. We combine secure multiparty computation and differential privacy to allow participants to leverage known trust dynamics which allow for increased ML model accuracy while preserving privacy guarantees and introduce an update auditor to protect against malicious participants launching dangerous label flipping data poisoning. We additionally introduce customizable modules into the TSC-PFed ecosystem which (a) allow users to customize the type of privacy protection provided and (b) provide a tiered participant selection approach which considers variation in privacy budgets. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings - 2021 3rd IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications, TPS-ISA 2021 | - |
dc.subject | federated-learning | - |
dc.subject | machine-learning | - |
dc.subject | privacy | - |
dc.subject | privacy-preserving-machine-learning | - |
dc.subject | security | - |
dc.subject | trust | - |
dc.title | The TSC-PFed Architecture for Privacy-Preserving FL | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TPSISA52974.2021.00052 | - |
dc.identifier.scopus | eid_2-s2.0-85128765442 | - |
dc.identifier.spage | 207 | - |
dc.identifier.epage | 216 | - |