Biography
I am a forth-year Ph.D student at CISPA Helmholtz Center for Information Security. My advisor is Dr. Yang Zhang. Prior to that, I obtained my bachelor (2017) and master (2020) degrees from Fudan University under the supervision of Prof. Yang Chen.
Research Interests
- Security and Privacy of Machine Learning
- Social Network Analysis
I’m looking for jobs from both acadamia and industry! Please drop me an email (xinlei.he@cispa.de) if you think I’d be a good fit for your team :D
Recent News
- [July 2023] One paper titled “You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content” got accepted in Oakland 2024!
- [July 2023] One paper titled “Test-Time Poisoning Attacks Against Test-Time Adaptation Models” got accepted in Oakland 2024!
- [May 2023] One paper titled “Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models” got accepted in CCS 2023!
- [April 2023] One paper titled “Data Poisoning Attacks Against Multimodal Encoders” got accepted in ICML 2023!
- [April 2023] One paper titled “Generated Graph Detection” got accepted in ICML 2023!
- [March 2023] I will join the TPC of Oakland 2024!
- [March 2023] We released MGTBench, a benchmark for the current machine-generated text (by ChatGPT) detection methods.
- [February 2023] One paper titled “Can’t Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders” got accepted in CVPR 2023!
- [February 2023] One paper titled “A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots” got accepted in USENIX Security 2023!
- [November 2022] One paper titled “On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning” got accepted in Oakland 2023!
- [July 2022] One paper titled “Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning” got accepted in ECCV 2022!
- [April 2022] One paper titled “SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders” got accepted in CCS 2022!
- [April 2022] One paper titled “Auditing Membership Leakages of Multi-Exit Networks” got accepted in CCS 2022!
- [March 2022] One paper titled “On Xing Tian and the Perseverance of Anti-China Sentiment Online” got accepted in ICWSM 2022!
- [March 2022] I Got The Norton Labs Graduate Fellowship (2022)!
- [December 2021] One paper titled “Model Stealing Attacks Against Inductive Graph Neural Networks” got accepted in Oakland 2022!
- [September 2021] One paper titled “ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models” got accepted in USENIX Security 2022!
- [September 2021] One paper titled “Quantifying and Mitigating Privacy Risks of Contrastive Learning” got accepted in CCS 2021!
- [May 2021] One paper titled “Trimming Mobile Applications for Bandwidth-Challenged Networks in Developing Regions” get accepted in TMC!
- [January 2021] One paper titled “DatingSec: Detecting Malicious Accounts in Dating Apps Using a Content-Based Attention Network” get accepted in TDSC!
- [September 2020] One paper titled “Stealing Links from Graph Neural Networks” got accepted in USENIX Security 2021!