arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.08421cs.CR
收藏

客户端协作分割学习

Client-Cooperative Split Learning

University of Technology Sydney(悉尼科技大学);CSIRO Data61(澳大利亚联邦科学与工业研究组织数据61);Edith Cowan University(伊迪丝科文大学)

Haiyu Deng, Yanna Jiang, Guangsheng Yu, Qin Wang, Xu Wang, Wei Ni, Shiping Chen, Ren Ping Liu

AI总结:

CliCooper是一种多客户端协作分割学习框架,通过隐私保护和信任机制提升模型训练的安全性和鲁棒性。

摘要:

模型训练正日益作为一项服务提供给资源受限的数据所有者,以构建定制化的模型。分割学习(SL)通过在隐私约束下将训练计算卸载,实现了这种服务,并演进到无服务器和多客户端设置,其中模型段被分布到训练客户端。这种协作模式假设部分信任:数据所有者隐藏标签和数据给训练客户端,而训练客户端产生可验证的训练成果和所有权证明。我们提出了CliCooper,一种多客户端协作SL框架,专门用于异构和部分信任环境中的协作模型训练服务,其中一名客户端贡献数据,而其他客户端共同作为SL训练者。CliCooper通过两个新设计弥合隐私和信任的差距。首先,基于差分隐私的激活保护和秘密标签混淆保护数据所有者的隐私,而不影响模型性能。其次,一种动态链式水印方案通过加密链接训练阶段上的模型段,确保可验证的训练完整性、鲁棒的模型溯源性和版权保护。实验表明,CliCooper在保持模型精度的同时,增强了对隐私和所有权攻击的抵抗力。它将聚类攻击的成功率(从中间激活推断标签组)降低到0%,将逆向重建(恢复训练数据)的相似度从0.50降至0.03,并限制基于模型提取的代理到约1%的准确率,与随机猜测相当。

英文摘要:

Model training is increasingly offered as a service for resource-constrained data owners to build customized models. Split Learning (SL) enables such services by offloading training computation under privacy constraints, and evolves toward serverless and multi-client settings where model segments are distributed across training clients. This cooperative mode assumes partial trust: data owners hide labels and data from trainer clients, while trainer clients produce verifiable training artifacts and ownership proofs. We present CliCooper, a multi-client cooperative SL framework tailored for cooperative model training services in heterogeneous and partially trusted environments, where one client contributes data, while others collectively act as SL trainers. CliCooper bridges the privacy and trust gaps through two new designs. First, differential privacy-based activation protection and secret label obfuscation safeguard data owners' privacy without degrading model performance. Second, a dynamic chained watermarking scheme cryptographically links training stages on model segments across trainers, ensuring verifiable training integrity, robust model provenance, and copyright protection. Experiments show that CliCooper preserves model accuracy while enhancing resilience to privacy and ownership attacks. It reduces the success rate of clustering attacks (which infer label groups from intermediate activation) to 0%, decreases inversion-reconstruction (which recovers training data) similarity from 0.50 to 0.03, and limits model-extraction-based surrogates to about 1% accuracy, comparable to random guessing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑