Probabilistic truncation has been widely used in a broad range of privacy-preserving machine learning (PPML) platforms, such as EdaBits (Crypto 20), ABY 2.0 (Usenix 21), Crypten (NIPS 21), Piranha-Falcon (Usenix 22), and Bicoptor (S&P 23), etc. In this work, we examine the problems of common probabilistic truncation protocols in PPML, and propose solutions from the perspectives of accuracy and efficiency. With regard to accuracy, we found the recommended precision parameters in many existing works are incorrect, leading to extremely low inference accuracy. We conducted a thorough analysis of their open-source code and found that their errors were mainly caused by simplified implementation; more specifically, random numbers are not correctly sampled in probabilistic truncation protocols. Based on this, we provide a detailed theoretical analysis to validate our views. With regard to efficiency, we identify limitations in the state-of-the-art secure comparison, Bicoptor’s (S&P 2023) DReLU protocol, which relies on the probabilistic truncation and is heavily constrained by the security parameter to eliminate errors, significantly impacting its performance. To address these challenges, we introduce a non-interactive deterministic truncation technique, replacing the original probabilistic truncation. Additionally, we propose a new technique for speeding up the ReLU/DReLU evaluation, which can be applied to the other non-linear functions as well. When the input size of DReLU is reduced to 7 bits, we can speed up approximately 5x the ReLU protocols w.r.t. ABY3, ABY2.0, EdaBits, and Bicoptor without compromising model accuracy. The improved protocol can complete a ReLU evaluation within 2 rounds and 704 bits overall communication when the input/output is secretly shared over the 64-bit ring, which yields a 92% communication reduction on original Bicoptor. Compared to existing PPML platforms with GPU acceleration, our benchmark indicates a 10x improvement in the DReLU protocol, and a 6x improvement in the ReLU protocol over Piranha-Falcon and a 3.7x improvement over Bicoptor. As a result, the overall PPML model inference could be sped up by 3-4 times.

The overhead of non-linear functions dominates the performance of the secure multiparty computation (MPC) based privacy-preserving machine learning (PPML). This work introduces a family of novel secure three-party computation (3PC) protocols, Bicoptor, which improve the efficiency of evaluating non-linear functions. The basis of Bicoptor is a new sign determination protocol, which relies on a clever use of the truncation protocol proposed in SecureML (S&P 2017). Our 3PC sign determination protocol only requires two communication rounds, and does not involve any preprocessing. Such sign determination protocol is well-suited for computing non-linear functions in PPML, e.g. the activation function ReLU, Maxpool, and their variants. We develop suitable protocols for these non-linear functions, which form a family of GPU-friendly protocols, Bicoptor. All Bicoptor protocols only require two communication rounds without preprocessing. We evaluate Bicoptor under a 3-party LAN network over a public cloud, and achieve more than 370,000 DReLU/ReLU or 41,000 Maxpool (find the maximum value of nine inputs) operations per second. Under the same settings and environment, our ReLU protocol has a one or even two orders of magnitude improvement to the state-of-the-art works, Falcon (PETS 2021) or Edabits (CRYPTO 2020), respectively without batch processing.

In recent years, the Ethereum platform has rapidly emerged, but its privacy issue has become the largest obstacle to the implementation of Ethereum projects. Unlike UTXO-based Bitcoin, Ethereum, the account-based blockchain, requires realtime updates of the account balance. Therefore, its corresponding hidden operation has certain difficulties. We propose a privacy protection scheme called RZcash to solve this problem. It implements the hiding of account balances that are updated in real time, and uses rangeproofs to ensure that the amount of each transaction does not exceed the payer's existing balance. For hiding the payee, we improve the related technology of Monero by using the ciphertext equivalent commitment scheme. We also provide the conversion mechanism and trading method between hidden coins and open coins and describe how RZcash can be combined with an existing account-based blockchain system (such as Ethereum). Finally, we implement the core model of RZcash and evaluate its performance. The evaluation results show that the scheme not only guarantees the privacy and security of the blockchain, but also has good performance in practical applications.

Information sharing solves the problem of information asymmetry between banks to a certain extent, but it also brings about the leakage of customer privacy. Therefore, how to protect data privacy while sharing data is an urgent issue. Blockchain protects the privacy of accounts and data while sharing data. Therefore, we propose a blockchain-based loan over-prevention mechanism. The program can hide the customer loan/repayment amount and thus protect the customer's privacy; we prove that the customer's loan amount is within a certain range and does not exceed the remaining loanable amount via a range proof. In order to share customer loan information between banks, we store the commitment of customers' amounts in the blockchain, and banks can obtain relevant information directly from the chain, which also reduces the amount of communication between banks. Finally, we implement the model and performe a performance analysis.