Xiaoyu Fang (Beijing University of Posts and Telecommunications), Shihui Zheng (Beijing University of Posts and Telecommunications), Lize Gu (Beijing University of Posts and Telecommunications)

Machine learning inference protocols based on semi-honest security models are vulnerable to attacks from malicious clients in real-world applications. These attacks can lead to the leakage of machine learning model parameters. Previous works introduced additional MACs computations to ensure correct client behavior. However, this resulted in higher runtime and communication costs during online inference.
In this work, we present CRISP, an efficient two-party cryptographic framework designed to defend against malicious clients. Specifically:
1)We design protocols for non-linear layers based on a new cryptographic primitive (Function Secret Sharing). The core of our approach focuses on optimizing the reconstruction process of MACs.
2)We propose a complex domain verification mechanism for linear layers. This mechanism eliminates the additional MACs computations by making better use of the complex space in homomorphic encryption CKKS.
Furthermore, in previous work (SIMC, USENIX Security'22), we identified compatibility issues in practical applications. The MAC reconstruction process in the nonlinear layers may leak intermediate inputs and outputs of the model when certain garbled circuit optimizations are applied. In contrast, CRISP effectively avoids this problem.
In secure inference benchmarks considered in SIMC, CRISP reduces the total communication cost of ML inference by up to 94% and cuts inference latency by up to 43%.

View More Papers

Losing the Beat: Understanding and Mitigating Desynchronization Risks in...

Zhi Li (Huazhong University of Science and Technology), Zhen Xu (Huazhong University of Science and Technology), Weijie Liu (Nankai University), XiaoFeng Wang (Nanyang Technological University), Hai Jin (Huazhong University of Science and Technology), Zheli Liu (Nankai University)

Read More

UIEE: Secure and Efficient User-space Isolated Execution Environment for...

Huaiyu Yan (Southeast University), Zhen Ling (Southeast University), Xuandong Chen (Southeast University), Xinhui Shao (Southeast University, City University of Hong Kong), Yier Jin (University of Science and Technology of China), Haobo Li (Southeast University), Ming Yang (Southeast University), Ping Jiang (Southeast University), Junzhou Luo (Southeast University, Fuyao University of Science and Technology)

Read More

Analysis of the Security Design, Engineering, and Implementation of...

Alan T. Sherman (University of Maryland, Baltimore County (UMBC)), Jeremy J. Romanik Romano (University of Maryland, Baltimore County (UMBC)), Edward Zieglar (University of Maryland, Baltimore County (UMBC)), Enis Golaszewski (University of Maryland, Baltimore County (UMBC)), Jonathan D. Fuchs (University of Maryland, Baltimore County (UMBC)), William E. Byrd (University of Alabama at Birmingham)

Read More