Meng Tong's Avatar
Meng Tong
童 蒙

Privacy Enhancement
& Trustworthy Machine Learning

I am a second-year Master student in cyberspace science at University of Science and Technology of China, advised by Prof. Kejiang Chen and Prof. Weiming Zhang. I am currently a research assistant at Purdue University, advised by Prof. Ninghui Li and working with Yuntao Du.

I was the captain of CTF team NEBULA, which ranked globally in the top 0.33%. During this time, I also served as a teaching assistant for Prof. Wenliang Du's SEED project.

Publications

[Security'26]

 Membership Inference Attacks on Tokenizers of Large Language Models
Meng Tong, Yuntao Du, Kejiang Chen,Weiming Zhang
In USENIX Security Symposium, 2026
[Paper] [Code]

[TL;DR: The first revelation of membership leakage from tokenizers of LLMs]

[NAACL'25, Oral]

 On the Vulnerability of Text Sanitization
Meng Tong, Kejiang Chen, Xiaojian Yuan, Jiayang Liu,Weiming Zhang, Nenghai Yu, Jie Zhang
In North American Chapter of the Association for Computational Linguistics, 2025
[Paper] [Code]

[TL;DR: Establish optimal reconstruction attacks against text sanitization]

[TDSC'25]

 InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model
Meng Tong, Kejiang Chen, Jie Zhang, Yuang Qi, Weiming Zhang, Tianwei Zhang, Zhikun Zhang
In IEEE Transactions on Dependable and Secure Computing, 2025
[Paper] [Code]

[TL;DR: The first implementation of differential privacy in text generation of LLMs]

Selected Honors & Awards

  • National Scholarship, China, 2025.
  • Distinguished Graduates, USTC, 2024.
  • Honors Bachelor from Gifted Student Program, USTC, 2024.
  • 2nd Prize in National University CTF Competition, China, 2023.
  • 2nd Prize in Strong Net CTF Competition, China, 2022.
  • 5th Place in Tencent Internation CTF Competition, Global, 2022.

Professional Experiences

  • Conference & Journal Reviewer:
     ACL ARR, AAAI, IEEE TIFS
  • External Reviewer:
     EuroS&P, NeurIPS, ICLR ,ICML, IEEE ToN