Hi, I am Yulong Ming!
RSS Feed- Research and education: PhD candidate in Computer Science at City University of Hong Kong (2022—26), interested in AI security, network security, and applied cryptography. BEng in Computer Science at University of Science and Technology of China (2018—22). Google Scholar , OpenReview , ORCID , and DBLP .
- Open source: I publish my own projects and contribute to free and open-source software (FOSS) projects on GitHub .
- Social media: I post in Chinese on 小红书 and Telegram . The content is mostly the same across platforms. Homepage: myl7.org . Email: i@myl7.org . For specific use cases, use research and general use . X (Twitter): @myl7s1 .
Recent Posts
-
P²RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval
Updated:Unlike existing systems, P²RAG avoids sorting candidate documents. Instead, it uses an interactive bisection method to determine the set of top-k documents. For security, P²RAG uses secret sharing on two semi-honest non-colluding servers to protect the data owner's database and the user's prompt. It enforces restrictions and verification to defend against malicious users and tightly bounds the information leakage of the database. The experiments show that P²RAG is 3--300× faster than the state-of-the-art PRAG for k = 16--1024.