An Ownership Verification Mechanism Against Encrypted Forwarding Attacks in Data-Driven Social Computing

An Ownership Verification Mechanism Against Encrypted Forwarding Attacks in Data-Driven Social Computing
复制标题

数据驱动的社交计算中针对加密转发攻击的所有权验证机制

DOI:
10.3389/fphy.2021.739259
复制
发表时间:
2021-09
影响因子:
3.1
通讯作者:
Yuanyuan He
Yuanyuan He
中科院分区:
物理与天体物理3区
文献类型:
--
作者:
Zhe Sun;Junping Wan;Bin Wang;Zhiqiang Cao;Ran Li;Yuanyuan He

文献摘要

参考文献

相似文献

数据驱动的深度学习加速了社交计算应用的普及。为了开发可靠的社交应用程序,服务提供商需要大量关于人类行为和交互的数据。由于这些数据与用户的隐私高度相关,研究人员对如何安全地构建协作训练模型进行了广泛的研究。密码学方法是协作训练的重要组成部分,用于保护梯度中的隐私信息。然而,加密的梯度是语义不可见的,因此很难检测到恶意参与者转发他人的梯度以不公平地获利。本文提出了一种基于P2P协议和Pedersen承诺的数据所有权验证机制,该机制可以帮助防止梯度窃取行为。我们在编码梯度上部署Paillier算法,以保护协作训练中的隐私信息。此外,我们还设计了一个统一的承诺方案,以批量方式完成承诺的验证过程,减少大规模社会计算中聚合器的验证消耗。实验结果表明了该机制的有效性和效率。
Data-driven deep learning has accelerated the spread of social computing applications. To develop a reliable social application, service providers need massive data on human behavior and interactions. As the data is highly relevant to users’ privacy, researchers have conducted extensive research on how to securely build a collaborative training model. Cryptography methods are an essential component of collaborative training which is used to protect privacy information in gradients. However, the encrypted gradient is semantically invisible, so it is difficult to detect malicious participants forwarding other’s gradient to profit unfairly. In this paper, we propose a data ownership verification mechanism based on Σ-protocol and Pedersen commitment, which can help prevent gradient stealing behavior. We deploy the Paillier algorithm on the encoded gradient to protect privacy information in collaborative training. In addition, we design a united commitment scheme to complete the verification process of commitments in batches, and reduce verification consumption for aggregators in large-scale social computing. The evaluation of the experiments demonstrates the effectiveness and efficiency of our proposed mechanism.
DOI: 10.1109/tifs.2017.2758756
发表时间: 2018-03
影响因子: 6.8
作者:
Jun Du;Chunxiao Jiang;Kwang-Cheng Chen;Yong Ren;H. Poor
通讯作者: Jun Du;Chunxiao Jiang;Kwang-Cheng Chen;Yong Ren;H. Poor
DOI: --
发表时间: 2022
期刊: IACR Cryptol. ePrint Arch.
影响因子: --
作者:
Xiaojie Guo;Zheli Liu;Jin Li;Jiqiang Gao;Boyu Hou-;Changyu Dong;T. Baker
通讯作者: Xiaojie Guo;Zheli Liu;Jin Li;Jiqiang Gao;Boyu Hou-;Changyu Dong;T. Baker
DOI: 10.1007/978-3-319-28166-7_1
发表时间: 2015-06
期刊: IACR Cryptol. ePrint Arch.
影响因子: --
作者:
Berry Schoenmakers;Meilof Veeningen
通讯作者: Berry Schoenmakers;Meilof Veeningen
DOI: 10.1007/978-1-4757-3296-2_7
发表时间: 2020-02
期刊: Definitions
影响因子: --
作者:
Nina Zahrai
通讯作者: Nina Zahrai
DOI: --
发表时间: 2016-10
期刊: ArXiv
影响因子: --
作者:
Jakub Konecný;H. B. McMahan;Daniel Ramage;Peter Richtárik
通讯作者: Jakub Konecný;H. B. McMahan;Daniel Ramage;Peter Richtárik