Yixin Liu (刘奕鑫)
Email: yila22 [AT] lehigh [.] edu
I am a 3rd-year CSE Ph.D. student working on Machine Learning at Lehigh University, advised by Prof. Lichao Sun. Previously, I obtained my B.E. of Software Engineering from South China University of Techology with honor in 2022. Feel free to contact me for any discussion or collaboration!
Research Interest
I am generally interested in the trustworthy and explainable generative AI and frontier models. My thesis research focus on data-centric approaches to safeguard user's data from unauthorized exploitation and provide source verification:
- Proactive Learnability Control [MetaCloak (CVPR'24 Oral), GraphCloak (Preprint), MUE (ICML'24 Workshop), SEM (AAAI'24 Oral), EditShield (ECCV'24)] : nowadays, user's private content is being largely exploited. Meanwhile, one funmental venerability of neural networks is that they are not robust to even small change in the input. By exploiting this property, we seek to safeguard the data from unauthorized model training without compromising the data utility.
- Watermarking and Verification [TextMarker (Preprint)]: As the growth of generative models, the boundary between real and fake is becoming more and more blurred. To provide a way for AI content attribution and training data source attributions, we seek to design robust watermarking and verification methods.
Reviewer Service
NeurIPS23, KDD23, CVPR24, ICML24, ECCV24 (Outstanding Reviewer), NeurIPS24, ICLR25, ICASSP25, CVPR25.
Publications ( show selected / show all by topic / show all by date )
Topics: Unauthorized Exploitation / NLP Safety / Explainable AI / Model Compresssion / Applications (*/†: indicates equal contribution.)
