Conan: Secure and reliable machine learning inference against malicious service providers
Publication Type
Journal Article
Publication Date
1-2026
Abstract
In the Machine Learning as a Service paradigm, a service provider (e.g., a server) hosting a model offers inference APIs to clients, who can send their queries and receive the inference results. While most recent secure inference works focus on addressing privacy issues, they overlook the importance of checking the service quality and reliability. A malicious server may deviate from the protocol specification to deliberately provide incorrect services such as using low-quality models. Thus, it is necessary to design new solutions to empower clients to verify the server’s model accuracy and inference integrity while protecting both parties’ privacy. We present Conan , a new secure and reliable inference framework against malicious servers to achieve accuracy verification, inference integrity, and privacy simultaneously. In Conan , the server first commits to the model and proves in zero-knowledge that the committed model achieves the claimed accuracy. Then both parties perform secure inference on the committed model against the malicious server. To instantiate the above framework, we design generic maliciously secure two-party computation (2PC) protocols with a fixed corrupted party, which may be of independent interest. Our protocols achieve high efficiency by utilizing the advantage that the semi-honest party can check the behavior of the corrupted party. Furthermore, they support both arithmetic and Boolean circuit evaluation, a crucial attribute for secure inference on complicated machine learning models. We implement the fixed-corruption 2PC protocols for our secure and reliable inference. The experimental results show 1∼2 orders of magnitude improvements over conventional maliciously secure protocols in terms of communication and computation costs.
Keywords
integrity, privacy, Secure inference, secure two-party computation, zero-knowledge proof
Discipline
Information Security
Publication
IEEE Transactions on Information Forensics and Security
Volume
21
First Page
1127
Last Page
1141
ISSN
1556-6013
Identifier
10.1109/TIFS.2025.3648121
Publisher
Institute of Electrical and Electronics Engineers
Citation
CHEN, Hanxiao; LI, Hongwei; HAO, Meng; XING, Pengzhi; HU, Jia; and JIANG, Wenbo.
Conan: Secure and reliable machine learning inference against malicious service providers. (2026). IEEE Transactions on Information Forensics and Security. 21, 1127-1141.
Available at: https://ink.library.smu.edu.sg/sis_research/11070
Additional URL
https://doi.org/10.1109/TIFS.2025.3648121