Contact Information

Department of Computer Science, Purdue University

Email: wang5327 AT purdue DOT edu, jerrywzl08 AT gmail DOT com

Biography

Google Scholar

ResearchGate

CV

Blog

Twitter

LinkedIn

Hiring! We have raised sufficient funding, and we are looking for a talented Software Engineer and a Data Engineer!

I am expected to graduate in December 2024.

I am Zhilin Wang, currently in my final year as a Ph.D. candidate in the Department of Computer Science at Purdue University, Indiana, USA. I’m also affiliated with CERIAS at Purdue. I obtained my bachelor’s degree at Nanchang University in June 2020 and commenced my doctoral journey at Purdue in January 2021. I am co-advised by Prof. Qin Hu and Prof. Snehasis Mukhopadhyay. I’ve actively contributed as a reviewer for prestigious academic journals and conferences such as IEEE TPDS, IEEE IoTJ, Elsevier JNCA, IEEE TCCN, and IEEE ICC. Additionally, I was a member of the Technical Program Committee (TPC) for the IEEE ICC’22 Workshop. My research interests are briefly described below:

• Decentralized Machine Learning. Implementing blockchain to achieve decentralized federated learning focuses on addressing resource allocation challenges on local and edge devices and straggler mitigation in a hierarchical system.
• Robust Machine Learning. Revealing the vulnerabilities of existing security mechanisms in federated learning and proposing lightweight and general schemes to protect industrial federated learning systems.
• Efficient Mobile Edge Computing. Designing efficient resource-sharing schemes to facilitate computational resource allocation on mobile edge servers.
• Large-scale Distributed Optimization. Designing efficient and robust distributed algorithms to solve large-scale optimization problems.
• Security & Privacy in Large Language Models. Toward improving the security and privacy protection of large language models during training and application.

In general, my research focuses on the system design, network optimization, and security protection of AI systems. If you are interested in my research, please directly email me.

News

• 10/2024: Our work, Can We Trust the Similarity Measurement in Federated Learning?, was accepted by IEEE Transactions on Information Forensics & Security!
• 02/2024: I published an AI-powered tool, Anton, to help users generate personalized resumes.
• 12/2023: Our work, Resource Optimization for Blockchain-based Federated Learning in Mobile Edge Computing, was accepted by IEEE Internet of Things Journal!
• 12/2023: I passed my Ph.D. preliminary exam!
• 10/2023: I published a Python package, xiezhi-ai, which can be used to do one-dimensional data anomaly detection!
• 03/2023: Our paper, Incentive Mechanism Design for Joint Resource Allocation in Blockchain-based Federated Learning, was accepted to IEEE Transactions on Parallel and Distributed Systems!

Education

• Ph.D., Purdue University, 01/2021-12/2024(expected)
• B.S., Nanchang University, 09/2016-06/2020

Working Experiences

• Co-founder and CTO, OpenJobs, San Francisco, USA, 04/2024-present.

  We have developed a cutting-edge job search engine that enables users to search for positions using their own words freely. In addition, they can access a comprehensive range of job-related information.

• Teaching Assistant, Purdue University, 01/2024-present.
• Research Assistant, Purdue University, 09/2021-12/2023.
• Student Tutor, Purdue University, 05/2022-09/2022.

Open Sourced Projects

1. Anton. AI-powered Resume Generation Tool.[link]

2. xiezhi-ai. The first one-dimensional anomaly detection tool. [Link]

3. HFL. A benchmark of hierarchical federated learning based on TensorFlow. [Code]

4. RL-based Knapsack Problem Solver. We provide a learning-based solution to multiple knapsack problems, which can get the approximate optimal solutions in polynomial time. [Code]

5. Blockchain-based FL. A user-friendly and robust blockchain-based federated learning framework in MEC will be applied to facilitate research and practical applications. [Code]

6. Correlated Equbirum Optimizer. An approximation method is provided. [Code]

Selected Publications

Journal Paper

1. IEEE TPDS：Wang Z, Hu Q, Li R, et al. Incentive Mechanism Design for Joint Resource Allocation in Blockchain-based Federated Learning[J], 2023. [Link] [PDF]

2. IEEE IoTJ：Wang Z, Hu Q, Xiong Z. Resource Optimization for Blockchain-based Federated Learning in Mobile Edge Computing[J], 2023. [Link]. [PDF].

3. Elsevier HCC: Wang Z, Hu Q, Wang Y, et al. Transaction Pricing Mechanism Design and Assessment for Blockchain[J]. High-Confidence Computing, 2021: 100044. [Link] [Code] [PDF]

4. IEEE IoTJ: Hu Q, Wang Z, Xu M, et al. Blockchain and Federated Edge Learning for Privacy-Preserving Mobile Crowdsensing[J]. IEEE Internet of Things Journal, 2021. [Link] [PDF] [NSF CRII]

5. IEEE IoTJ: Peng C, Hu Q, Wang Z, et al. “Online Learning based Fast-Convergent and Energy-Efficient Device Selection in Federated Edge Learning.” IEEE Internet of Things Journal (2022). [Link] [PDF]

Conference Paper

1. IEEE MASS’22: Wang Z, Qin Hu, et al. Blockchain-based Edge Resource Sharing for Metaverse. IEEE MASS 2022. [Link] [Code] [PDF]

2. IEEE WCNC’22: Wang Z, Qiao Kang, Xinyi Zhang, Qin Hu, Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey, IEEE WCNC 2022. [Link] [PDF]

3. IEEE ICBC’20: Hu Q, Nigam Y, Wang Z, et al. A Correlated Equilibrium based Transaction Pricing Mechanism in Blockchain[C]//2020 IEEE International Conference on Blockchain and Cryptocurrency (ICBC). IEEE, 2020: 1-7. [Link] [Code] [PDF]

Working Paper

The following papers are on arXiv or submitted to journals and conferences:

1. Wang Z, Hu Q, blockchain-based Federated Learning: A Comprehensive Survey. [Link] [PDF]. Will be submitted to IEEE Communications Surveys & Tutorials.
2. Wang Z, Hu Q et al. Straggler Mitigation and Latency Optimization in Blockchain-based Hierarchical Federated Learning. [Link]. [PDF]. Submitted to IEEE TVT.
3. Li S, Hu Q, and Wang Z*. PoFEL: Energy-efficient Consensus for Blockchain-based Hierarchical Federated Learning. Submitted to IEEE TMC.
4. Wang Z, Hu Q et al. Can We Trust the Similarity Measurement in Federated Learning? Submitted to IEEE TIFS, Major Revision.
5. Wang Z, Hu Q. A Robust federated learning algorithm. Will be submitted to S&P ‘25.

Supervised Students

The students below are all from the CS department at Purdue. They performed excellently during the time they worked with me.

Undergraduates

1. Garrett Sanders (Graduated in May 2022)

2. Minh Khuat (Graduated in May 2022)

3. Samuel Sibhatu

4. Richard Ekwenibe

5. Xinyi Zhang (Graduated in May 2023)

Master Students

1. Arushi Pandit

2. Akshita Gupta

3. Joe Kang (Graduated in Dec 2022)

4. Deepak Chinthada

The following interns did an outstanding job in working on projects with me.

1. Ruiyang Qin (Tongji University)
2. Ruifeng Li (Shanghai University)

Teaching

Spring 2024: CSCI 59000/49000 Wireless And Mobile Security

Fall 2024: CSCI 45900 Capstone Project

Talks

1. 2024/5/21, Falcon Talent, How GenAI can Influence the Recruitment Industry?