Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction
Author:
Affiliation:
1. School of Computing, Engineering, and Mathematical Sciences (SCEMS), La Trobe University, Melbourne, VIC, Australia
2. CSIRO’s Data61, Eveleigh, NSW, Australia
Funder
Australian Research Council through the DECRA project
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Computer Networks and Communications,Safety, Risk, Reliability and Quality
Link
http://xplorestaging.ieee.org/ielx7/10206/9970396/10121474.pdf?arnumber=10121474
Reference53 articles.
1. Inverting gradients—How easy is it to break privacy in federated learning?;geiping;Proc Adv Neural Inf Process Syst,2020
2. Split computing and early exiting for deep learning applications: Survey and research challenges;matsubara;ACM Comput Surv,2022
3. PPA: Preference profiling attack against federated learning;zhou;arXiv 2202 04856,2022
4. SplitFed: When Federated Learning Meets Split Learning
Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Incentivizing Participation in SplitFed Learning: Convergence Analysis and Model Versioning;2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS);2024-07-23
2. Design of an efficient dynamic context‐based privacy policy deployment model via dual bioinspired Q learning optimisations;IET Cyber-Physical Systems: Theory & Applications;2024-06-27
3. Impact of Neural Network Depth on Split Federated Learning Performance in Low-Resource UAV Networks;2024 International Wireless Communications and Mobile Computing (IWCMC);2024-05-27
4. Split Federated Learning for 6G Enabled-Networks: Requirements, Challenges, and Future Directions;IEEE Access;2024
5. Systematic Evaluation of Robustness Against Model Inversion Attacks on Split Learning;Lecture Notes in Computer Science;2024
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3