首页|Guizhou University Researcher Reveals New Findings on Machine Learning (Federated Learning Backdoor Attack Based on Frequency Domain Injection)
Guizhou University Researcher Reveals New Findings on Machine Learning (Federated Learning Backdoor Attack Based on Frequency Domain Injection)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Mdpi
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on artificial intelligence have been published. According to news reporting from Guiyang, People’s Republic of China, by NewsRx journalists, research stated, “Fed- erated learning (FL) is a distributed machine learning framework that enables scattered participants to collaboratively train machine learning models without revealing information to other participants.” Funders for this research include National Key Research And Development Program of China; National Natural Science Foundation of China; Guizhou Science Contract Plat Talent; Research Project of Guizhou University For Talent Introduction; Cultivation Project of Guizhou University, Pr China; Open Fund of Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Pr China. Our news editors obtained a quote from the research from Guizhou University: “Due to its distributed nature, FL is susceptible to being manipulated by malicious clients. These malicious clients can launch backdoor attacks by contaminating local data or tampering with local model gradients, thereby damaging the global model. However, existing backdoor attacks in distributed scenarios have several vulnerabilities. For example, (1) the triggers in distributed backdoor attacks are mostly visible and easily perceivable by humans; (2) these triggers are mostly applied in the spatial domain, inevitably corrupting the semantic information of the contaminated pixels. To address these issues, this paper introduces a frequency-domain injection-based backdoor attack in FL.”
Guizhou UniversityGuiyangPeople’s Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
Mdpi
