Paper 2023/1729
CompactTag: Minimizing Computation Overheads in Actively-Secure MPC for Deep Neural Networks
Abstract
Secure Multiparty Computation (MPC) protocols enable secure evaluation of a circuit by several parties, even in the presence of an adversary who maliciously corrupts all but one of the parties. These MPC protocols are constructed using the well-known secret-sharing-based paradigm (SPDZ and SPD
Metadata
- Available format(s)
-
PDF
- Category
- Cryptographic protocols
- Publication info
- Preprint.
- Keywords
- Machine LearningSecure ComputationNeural NetworksDishonest MajorityPPML
- Contact author(s)
-
yongqin @ usc edu
pratik93 @ bu edu
kotis @ iisc ac in
arpita @ iisc ac in
annavara @ usc edu - History
- 2023-11-13: approved
- 2023-11-08: received
- See all versions
- Short URL
- https://ia.cr/2023/1729
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2023/1729, author = {Yongqin Wang and Pratik Sarkar and Nishat Koti and Arpita Patra and Murali Annavaram}, title = {{CompactTag}: Minimizing Computation Overheads in Actively-Secure {MPC} for Deep Neural Networks}, howpublished = {Cryptology {ePrint} Archive, Paper 2023/1729}, year = {2023}, url = {https://eprint.iacr.org/2023/1729} }