Jie Ren

Exciting News! Our new paper on memorization in text-to-image diffusion is now available. We delve into the understanding of memorization via attention, and throw a light on the internal model behavior when memorization happens. Please find our paper at arxiv.org/abs/2403.11052

Our paper for LLM watermark is accepeted by NAACL findings! We proposed a new method to strengthen the robustness of watermark agains paraphrase using the semantics. This is very meaningful factor for the practical application! Please find the paper at openreview.net/forum?id=hbMR7…

🔥Presenting the new addition to our series: FT-Shield!🛡️Building on the success of DiffusionShield, we delve deeper into the challenge of copyright in fine-tuning of text-to-image diffusion models: 📎 DiffusionShield: arxiv.org/abs/2306.04642 📎 FT-Shield: arxiv.org/abs/2310.02401