Xiangtao Meng's Homepage
 |
Xiangtao Meng 孟祥涛2th-year Ph.D, ISecLab |
News:
2025-8-13: One paper titled “DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation” got accepted in CCS 2025! Congratulations to Xinyu!!! First time as a corresponding author.
2025-3-11: One paper titled “Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models” got accepted in IEEE S&P 2025! Congratulations to Yingkai!!!
2024-11-15: My master's thesis, titled “Robustness Research on Deepfake Detection Technology,” has been recognized as an outstanding master's thesis at Shandong University.
2023-11-12: One paper titled “AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection” got accepted in IEEE S&P 2024!
2023-10-13: One paper titled “DEEPFAKER: A Unified Evaluation Platform for Facial Deepfake and Detection Models” got accepted in TOPS(ACM Transactions on Privacy and Security) 2024!
Education
Sep 2023 - Present: Ph.D，in School of Cyber Science and Technology, Shandong University，supervised by Prof. Xiaoyun Wang and Prof. Shanqing Guo, Qingdao, China.
Sep 2020 - Jun 2023: M.Sc. in School of Cyber Science and Technology, Shandong University，supervised byProf. Shanqing Guo, Qingdao, China.
Sep 2016 - Jun 2020: B.Sc. in Network Engineering, Shandong University of Science and Technology, Qingdao, China.
Research Interests
My research centers on Trustworthy Machine Learning (expercially DeepFake), including disclosing the safety, security and privacy of the Machine Learning (such as, Text-to-Image, ChatGPT, etc.) and proposing corresponding defense measures.
Publication
Xinyu, Xiangtao Meng✉, Yingkai Dong, Zheng Li✉, Shanqing Guo✉. DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation. CCS 2025. TOP A*
Yingkai Dong, Xiangtao Meng, Ning Yu, Zheng Li✉, Shanqing Guo✉. Fuzz-testing meets llm-based agents: An automated and efficient framework for jailbreaking text-to-image generation models. IEEE S&P 2025. TOP A* arxiv. PDF]
Xiangtao Meng, Li Wang, Shanqing Guo✉, Lei Ju, Qingchuan Zhao. AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection. IEEE S&P 2024. TOP A* PDF] Code]
Li Wang, Xiangtao Meng, Dan Li, Xuhong Zhang, Shouling Ji, Shanqing Guo✉. DEEPFAKER: A Unified Evaluation Platform for Facial Deepfake and Detection Models. ACM Transactions on Privacy and Security (TOPS) 2024. B* PDF]
✉ Corresponding author.