About Me

I am a third-year graduate student at KAUST and am very fortunate to be advised by Prof. Di Wang. My primary research goal is to reduce the gap between personal data protection requirements and real-world organizations’ workflows. Specifically, I'm interested in provable machine unlearning.  I'm also interested in secure algorithms and their applications on real-world settings (Hardware, Healthcare, Finance, System ...). Please get in touch with me if you would like to discuss potential research collaborations. 

 What's New

• [May 2024] Received EPFL - SURI Fellowship. Will present our work on machine unlearning measurements in Lausanne~ Thanks EPFL! 

• [May 2024] I am invited as a reviewer of IEEE TIFS.

• [Apr 2024] Our paper "Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness" has been released (https://arxiv.org/abs/2403.12830).

• [Dec 2023] Our paper "Communication Efficient and Provable Federated Unlearning" has been accepted at the 50th International Conference on Very Large Databases (VLDB 2024).

• [Sep 2023] Received the CEMSE Dean's List Award, KAUST, 2023.

• [Jul 2023] Received the USENIX Security '23 Student Grant.

• [Apr 2023] Our paper "High Dimensional Statistical Estimation under Uniformly Dithered One-bit Quantization" has been accepted at IEEE Transactions on Information Theory (TIT).

• [Apr 2023] Our paper "Inductive Graph Unlearning" has been accepted at the 32nd USENIX Security Symposium (USENIX 2023).

• [Dec 2022] I am invited as a reviewer of IEEE TNNLS.

• [Jul 2022] Newly affiliated as a PhD Student with the SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence (SDAIA-KAUST AI).