|
Boyang Zheng I'm currently a junior-year student, a member of Shanghai Jiao Tong University, ACM Honor Class. I'm also an intern at Shanghai AI Lab, advised by Chao Dong. My current research interests include computer vision, self-supervised learning, and multi-modal learning. I'm also interested at generative models, which are incredibly popular nowadays. In the realm of academic, I have little interest in chasing the state-of-the-art unless I have to. Instead, I prefer to explore intersting ideas that help better understanding of this field or could possibly lead to new applications. Apart from pure academic pursuit, I also devote myself to use AI for social good, such as copyright protection, fairness and so on. In this regard, I'm also a member of MIST, a project aiming to protect the copyrighted artworks. Email / CV / Google Scholar / Github |
|
News[2023-9-25] Internship begins! I'm now an intern at Shanghai AI Lab, advised by Chao Dong, doing research on MLLM and their possible applications on low-level vision tasks. |
Publications |
|
ACE: Improving Adversarial Attacks on Latent Diffusion Model
Boyang Zheng*, Chumeng Liang*, Xiaoyu Wu, Yan Liu, arXiv, 2023 code / paper / public release for artists(also known as mist-v2) A method to craft adversarial examples for Latent Diffusion Model against various personlization techniques(e.g. SDEdit, LoRA), strongly outperforming existing methods. We aim for protecting the privacy of artists and their copyrighted works in the era of AIGC. |
|
This website is a modification of Jon Barron's Website. |