I am currently a postdoc (Shuimu Tsinghua Scholar, 水木学者) at Institute for Advanced Study, Tsinghua University (IASTU) hosted by Academician Prof. Xiaoyun Wang.Contact
- Address: Room 401, Science Building, Tsinghua University, Beijing 100084, China
- E-mail: congtianshuo AT tsinghua DOT edu DOT cn
Research Interests
- Trustworthy Machine Learning
- Secure Multi-party Computation
- Lightweight Cipher Design
Education
- Tsinghua University
- 08.2017 - 06.2023, Beijing, China
- Ph.D. in Mathematics at Institute for Advanced Study
- Advisor: Academician Prof. Xiaoyun Wang (IACR Fellow)
- CISPA Helmholtz Center for Information Security
- 08.2021 - 01.2023, Saarbrücken, Germany
- Visiting Ph.D. student at CISPA
- Advisor: Dr. Yang Zhang
- Tsinghua University
- 08.2013 - 06.2017, Beijing, China
- B.Eng. in Electronic Engineering
- Advisor: Prof. Yong Ren
Services
- PC Member
- 2024: ACSAC, CSCW, CVPR, MM, ECCV
- 2023: CCS (Artifact Evaluation), NeurIPS workshop on New In ML
- Journal Reviewer
- 2024: TDSC, TOPS, TKDD
- 2023: PeerJ Computer Science
- Organizer
- External Reviewer
- 2024: S&P, USENIX Security
- 2023: ICLR, WWW, SaTML, SecureComm
- 2022: CCS, ICLR, ESORICS, PETS, SAC, AsiaCCS, SocInfo, EdgeSys, AISec
- 2020: AsiaCrypt
News
- [Mar. 12, 2024] Became an invited reviewer of ECCV 2024.
- [Feb. 08, 2024] Invited to serve on the PC of ACSAC 2024.
- [Jan. 09, 2024] Check out a curated reading list on safety, security, and privacy of large models!
- [Dec. 15, 2023] Gave a talk titled "Attack AI models: From ResNet to GPT-4" at Xi'an Jiaotong University!
- [Dec. 13, 2023] Became an invited reviewer of ACM TOPS.
- [Dec. 05, 2023] Became an invited reviewer of IEEE TDSC.
- [Nov. 10, 2023] We proposed FigStep, a quite simple yet effective jailbreaking algorithm against large vision-language models (VLMs)!
- [Nov. 09, 2023] Became an invited reviewer of CVPR 2024.
- [Nov. 06, 2023] Became an invited reviewer of ACM TKDD.
- [Oct. 21, 2023] Served on the AEC of CCS 2023.
- [Aug. 16, 2023] One technical report titled "Robustness Over Time: Understanding Adversarial Examples’ Effectiveness on Longitudinal Versions of Large Language Models" was released!
- [Jul. 26, 2023] Gave a talk titled "Privacy and Security Analysis of Deep Learning" at Harbin Institute of Technology (Shenzhen)!
- [Jul. 11, 2023] One paper titled “Test-time Poisoning Attacks Against Test-time Adaptation Models” got accepted in IEEE S&P (Oakland) 2024!
- [Jul. 06, 2023] I joined Tsinghua IAS as a postdoc and was selected as "Shuimu Tsinghua Scholar"!
- [May. 18, 2023] Successfully passed the Ph.D. defense!
- [Apr. 23, 2022] One paper titled “SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders” got accepted in ACM CCS 2022!
- [Aug. 15, 2021] Started my visiting Ph.D. at CISPA Helmholtz Center for Information Security, Saarbrücken, Germany!