Collusion-Resistant Privacy-Preserving Outsourced Training Under Single Cloud With Semi-Honest TEE

In the era of big data, leveraging multi-party data for model training has become essential to overcome the limitations of single-source data. However, the integration and processing of data are restricted by stringent laws and regulations to ensure privacy. Although some privacy-preserving multi-party training schemes have been proposed, they still face limitations in computation, communication, or security. In this paper, we propose PACLR and PACLR<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^+$</tex-math></inline-formula> to achieve collusion-resistant privacy-preserving outsourced training under single cloud with semi-honest TEE. PACLR protects data security, while PACLR<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^+$</tex-math></inline-formula> ensures the security of both data and model parameters. Specifically, we introduce a trust-enhanced and secure outsourcing training approach that eliminates the need for a trusted third party to initialize the system and achieves secure data outsourcing. Then, we present a privacy-preserving training method over packed ciphertext using mini-batch stochastic gradient descent to balance efficiency and accuracy. Additionally, we propose some optimization approaches to improve training efficiency. Detailed security analysis confirms that our schemes are privacy-preserving and can resist various collusion attacks. Extensive experiments on real datasets demonstrate the effectiveness of our schemes, showing superior efficiency compared to recent scheme.