Enclave Tree: Privacy-preserving Data Stream Training and Inference Using TEE

Wang，Qifan1; Cui，Shujie2; Zhou，Lei3; Wu，Ocean1; Zhu，Yonghua1; Russello，Giovanni1

10.1145/3488932.3517391

2022-05-30

17th ACM ASIA Conference on Computer and Communications Security 2022 (ACM ASIACCS)

ASIA CCS 2022 - Proceedings of the 2022 ACM Asia Conference on Computer and Communications Security

741-755

MAY 30-JUN 03, 2022

null,Nagasaki,JAPAN

1601 Broadway, 10th Floor, NEW YORK, NY, UNITED STATES

ASSOC COMPUTING MACHINERY

The classification service over a stream of data is becoming an important offering for cloud providers, but users may encounter obstacles in providing sensitive data due to privacy concerns. While Trusted Execution Environments (TEEs) are promising solutions for protecting private data, they remain vulnerable to side-channel attacks induced by data-dependent access patterns. We propose a Privacy-preserving Data Stream Training and Inference scheme, called EnclaveTree, that provides confidentiality for user's data and the target models against a compromised cloud service provider. We design a matrix-based training and inference procedure to train the Hoeffding Tree (HT) model and perform inference with the trained model inside the trusted area of TEEs, which provably prevent the exploitation of access-pattern-based attacks. The performance evaluation shows that EnclaveTree is practical for processing the data streams with small or medium number of features. When there are less than 63 binary features,EnclaveTree is up to ∼10x and ∼9 faster than naïve oblivious solution on training and inference, respectively.

data stream data-oblivious hoeffding tree sgx enclave

Others

English

EI ; CPCI-S

null[UOWX1503]

Computer Science ; Mathematics ; Telecommunications

Computer Science, Information Systems ; Computer Science, Theory & Methods ; Mathematics, Applied ; Telecommunications

WOS:000937026200055

20222712310659

Forestry ; Privacy-preserving techniques ; Side channel attack ; Trees (mathematics) ; Trusted computing

Telecommunication; Radar, Radio and Television:716 ; Telephone Systems and Related Technologies; Line Communications:718 ; Data Processing and Image Processing:723.2 ; Agricultural Equipment and Methods; Vegetation and Pest Control:821 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4

2-s2.0-85133170666

Scopus

1.The University of Auckland,Auckland,New Zealand
2.Monash University,Melbourne,Australia
3.Southern University of Science and Technology,Shenzhen,China

Wang，Qifan,Cui，Shujie,Zhou，Lei,et al. Enclave Tree: Privacy-preserving Data Stream Training and Inference Using TEE[C]. 1601 Broadway, 10th Floor, NEW YORK, NY, UNITED STATES:ASSOC COMPUTING MACHINERY,2022:741-755.