arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.12709quant-phcs.AIcs.CRcs.DC
收藏

在多用户量子网络上实验验证的量子安全联邦学习

Experimentally validated quantum-secure federated learning over a multi-user quantum network

National Laboratory of Solid State Microstructures(固态微结构国家实验室);School of Physics, Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing 210093, China(物理系,先进微结构协同创新中心,南京大学,南京210093,中国);School of Physics(物理系);Key Laboratory of Quantum State Construction(量子态制备重点实验室);Manipulation (Ministry of Education), Renmin University of China, Beijing 100872, China(操控(教育部),中国人民大学,北京100872,中国)

Zhi-Ping Liu, Xiao-Yu Cao, Hao-Wen Liu, Xiao-Ran Sun, Yu Bao, Jian-Yu Shen, Yu-Shuo Lu, Hua-Lei Yin, Zeng-Bing Chen

AI总结:

本文提出QuNetQFL协议,通过分布式量子密钥掩蔽局部模型更新,实现信息论安全的聚合。实验验证在四客户端量子网络上,提升分类准确率并展示在语言任务和大规模模拟中的扩展性。

摘要:

联邦学习实现了去中心化和隐私保护的训练,但在量子时代仍面临隐私泄露的风险。量子联邦学习(QFL)提供了一条通往增强安全性和效率的途径。然而,缺乏一个实际且经过实验验证的QFL协议,利用近期量子技术解决数据隐私问题。本文提出了QuNetQFL协议,在量子网络上实现,其中局部模型更新被分布式量子秘密密钥掩蔽,提供信息论安全的聚合。我们实验验证该协议在四客户端量子网络上,并通过生成的密钥在量子和现实数据集上进行性能基准测试。添加一个量子客户端显著提高了对多体纠缠和非稳定器量子数据集的分类准确率。在语言任务中,我们通过联邦微调混合经典-量子语言模型进行情感分析,实现了在模拟和真实量子硬件上的可比和稳健性能。大规模模拟进一步展示了其扩展性,可扩展到200个客户端进行手写数字识别,具有快速收敛和通信成本减少75%的模型压缩。本文的工作为新兴量子互联网中的量子安全联邦学习建立了实际和可扩展的路线。

英文摘要:

Federated learning enables decentralized, privacy-preserving training but remains vulnerable to privacy leakage in the quantum era. Quantum federated learning (QFL) offers a promising path towards enhanced security and efficiency. However, a practical and experimentally validated QFL protocol utilizing near-term quantum techniques to address data privacy has been lacking. Here we present QuNetQFL, a QFL protocol implemented on quantum networks, in which local model updates are masked with distributed quantum secret keys, offering information-theoretic security during aggregation. We experimentally validate the protocol on a four-client quantum network and benchmark its performance using the generated keys on quantum and real-world datasets. Adding a single quantum client significantly improves global accuracy for classifying multipartite entangled and non-stabilizer quantum datasets. For language tasks, we apply QuNetQFL to sentiment analysis by federated fine-tuning of a hybrid classical-quantum language model, achieving comparable and robust performance in simulation and on real quantum hardware. Large-scale simulations further demonstrate scalability to 200 clients for handwritten-digit recognition, with rapid convergence and a $75\%$ reduction in communication cost via model compression. Our work establishes a practical and scalable route to quantum-secure federated learning for the emerging quantum internet.

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。

↑