.png){kind=icon}
Return
VerifyTL: Secure and Verifiable Collaborative Transfer Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TDSC.2023.3241181.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Getting access to labeled datasets in certain sensitive application domains can be challenging. Hence, one may resort to transfer learning to transfer knowledge learned from a source domain with sufficient labeled data to a target domain with limited labeled data. However, most existing transfer learning techniques only focus on one-way transfer which may not benefit the source domain. In addition, there is the risk of a malicious adversary corrupting a number of domains, which can consequently result in inaccurate prediction or privacy leakage. In this paper, we construct a secure and Verifiable collaborative Transfer Learning scheme, VerifyTL, to support two-way transfer learning over potentially untrusted datasets by improving knowledge transfer from a target domain to a source domain. Furthermore, we equip VerifyTL with a secure and verifiable transfer unit employing SPDZ computation to provide privacy guarantee and verification in the multi-domain setting. Thus, VerifyTL is secure against malicious adversary that can compromise up to n - 1 out of n data domains. We analyze the security of VerifyTL and evaluate its performance over four real-world datasets. Experimental results show that VerifyTL achieves significant performance gains over existing secure learning schemes.
Keywords:
Convolutional neural network
dishonest majority
malicious security
spdz
transfer learning
Journal
IF:
7.5
Papers:
2.6K
Citations:
9.6K
Organization
Cited Papers
NMR Evidence for a Short, Strong Hydrogen Bond at the Active Site of a Cholinesterase.png)
Biochemistry
BiochemistryIF0
PREAI
ShareSaveShareSave
Adaptation of the communicative brain to post-lingual deafness. Evidence from functional imaging
PREAI
ShareSaveShareSave
View more