Meng Tong
Source-listed: Final-year Master's candidate in cybersecurity · University of Science and Technology of China (USTC)
- Language models
Selected work
5- Membership Inference Attacks on Tokenizers of Large Language ModelsFirst author · 2026
- On the Vulnerability of Text SanitizationFirst author · 2025
- InferDPT: Privacy-Preserving Inference for Closed-Box Large Language ModelsFirst author · 2025
- InferDPT (official implementation)Contributor
- Tokenizer-MIAContributor