24小时热门版块排行榜

返回列表

liupkumse

铁虫 (初入文坛)

应助: 3 (幼儿园)
金币: 215
帖子: 32
在线: 30.3小时
虫号: 2543003
注册: 2013-07-12
性别: GG
专业: 计算机软件

[交流] 英国斯旺西大学计算机系招收全奖PhD，联邦学习方向

大佬们好，在下目前有个英国斯旺西大学计算机系的全奖phd名额，奖学金涵盖国际学费和年度生活津贴，课题的主要领域是联邦学习，提交申请的ddl是10月15日，入学时间是明年1月（别问我为啥时间这么紧张。。学校就是这么通知我的

）。不过实在赶不上的晚一点入学，到明年5月入学季再来应该也ok。

该phd学制是4年，其中75%的时间做research，25%的时间做ta，ta期间可以拿到英国这边的教师资格证，对毕业后有意在英联邦国家做教职的同学比较有意义。总体而言英国这边国际生奖学金的机会其实不太多，这几年整体经济形势也确实不太好，大学花钱都扣扣搜搜的，挤出来一个国际生奖学金名额也挺不容易的。目前这个奖学金cover每年20几万的学费和每年18万左右的生活费，4年读下来貌似也可以看作赚了150万人民币了？

项目具体信息请见附图，欢迎感兴趣的同学通过【邮件】与我联系，邮件中可附上常规申请材料（成绩单、cv等）。

【学校简介】
斯旺西大学位于英国威尔士的第二大城市（cūn）斯旺西市（swansea）。该市是全英第五安全的城市，是个海滨城市，英国最美海滩之一的rhossili也在这。学校始建于1920年，qs 2025排名为298位。总体来说当地环境安全、风景不错、生活成本低、不卷（划重点），学校的更多信息请感兴趣的同学自行搜索。

【导师简介】
dr. yang liu received his d.phil. in computer science from the university of oxford in july 2018. he is currently a senior lecturer in the department of computer science at swansea university. before joining swansea university, he served as an assistant professor at the harbin institute of technology in shenzhen from 2018 to 2024. his research interests focus on data security and privacy-preserving computing. he has expertise in federated learning, blockchain applications, and the design of privacy protection mechanisms. his current work explores the convergence of artificial intelligence and cybersecurity technologies, aiming to enhance the robustness and security of intelligent systems.

【项目简介】
project description:
the department of computer science of swansea university is offering graduate teaching assistantships for january 2025 entry to its phd studies in computer science. this position is ideal for candidates with a keen interest in pursuing doctoral research in cyber security, particularly focusing on privacy, security, and robustness in federated learning (fl). successful applicants will also have the opportunity to gain valuable teaching training and experience while developing their professional skills. the gta will complete the associate fellowship of advance he (afhea) and thereby develop their teaching related skills and enhance their professional competencies. the equivalent of 3 months per year will be devoted to teaching training/practice, the remaining time is for research studies on a four year programme.

research topic: privacy and robustness in federated learning
as the deployment of federated learning (fl) expands across various domains, so do the challenges related to privacy, security, and robustness. its distributed nature introduces unique vulnerabilities that traditional centralized learning approaches do not face. attacks on fl can result in significant privacy breaches, compromising sensitive data across multiple participants.
this phd project focuses on the exploration and analysis of threats, attacks, and defenses within fl environments. the aim is to build a comprehensive understanding of the vulnerabilities in fl systems, design robust countermeasures, and establish guidelines for secure and privacy-preserving fl implementations. the project will not only focus on theoretical advancements but also emphasize practical applications in real-world scenarios. the successful candidates will have the opportunity to collaborate with a multidisciplinary team, including experts from both academia and industry, to ensure the research outcomes are both innovative and impactful.the ideal candidate should be passionate about tackling complex challenges at the intersection of ai, privacy, and security , and eager to contribute to both academic research and teaching.

key objectives:
1. investigate federated learning threats: conduct a deep dive into potential attacks on fl systems, including poisoning attacks, backdoor attacks, and inference attacks. understand how these attacks exploit the distributed nature of fl to breach privacy and compromise model integrity.
2. design defensive mechanisms: develop advanced defense strategies against the identified attacks. this includes exploring techniques like differential privacy, secure aggregation, and adversarial training to enhance the robustness and privacy of fl models.
3. real-world application and validation: implement and test the developed models on real-world datasets from domains such as healthcare, finance, or iot. validate the effectiveness of the proposed defenses in preserving privacy and robustness under adversarial conditions.

contact details for enquires:
dr. yang liu
https://yangliu.info

更新一下，申请DDL推迟到了10月23日。国际生建议选择4月入学，以预留充足的时间申请ATAS和VISA。具体项目信息可见官网链接：

官网链接

回复此楼