C
Chongzhi Gao
Researcher at Guangzhou University
Publications - 48
Citations - 2133
Chongzhi Gao is an academic researcher from Guangzhou University. The author has contributed to research in topics: Encryption & Cloud computing. The author has an hindex of 17, co-authored 41 publications receiving 1447 citations. Previous affiliations of Chongzhi Gao include Fujian Normal University & Sun Yat-sen University.
Papers
More filters
Journal ArticleDOI
Multi-key privacy-preserving deep learning in cloud computing
TL;DR: This work presents a basic scheme based on multi-key fully homomorphic encryption (MK-FHE), and proposes a hybrid structure scheme by combining the double decryption mechanism and FHE, and proves that these two multi- key privacy-preserving deep learning schemes over encrypted data are secure.
Journal ArticleDOI
Privacy-preserving outsourced classification in cloud computing
TL;DR: This work proposes a framework for privacy-preserving outsourced classification in cloud computing (POCC), and proves that the scheme is secure in the semi-honest model.
Journal ArticleDOI
Secure Multi-Party Computation: Theory, practice and applications
TL;DR: This paper presents a comprehensive survey on the theoretical and practical aspects of SMPC protocols, including its security requirements and basic construction techniques, and summarizes the concrete application-oriented protocols that are currently available.
Journal ArticleDOI
Privacy-preserving Naive Bayes classifiers secure against the substitution-then-comparison attack
TL;DR: This paper proposes a scheme which avoids information leakage under the substitution-then-comparison (STC) attack, and uses a “double-blinding” technique and shows how to combine it with additively homomorphic encryptions and oblivious transfer to hide both parties’ privacy.
Journal ArticleDOI
Dynamic Fully Homomorphic encryption-based Merkle Tree for lightweight streaming authenticated data structures
TL;DR: This work presents the fully dynamic FHMT construction, which is a construction that is able to authenticate an unbounded number of data elements and improves upon the state-of-the-art in terms of computational overhead.