Meta tags:

Headings (most frequently used words):

xiaoyu, wu, nicholas, 吴晓宇, news,

Text of the page (most frequently used words):
and (10), 2025 (6), #xiaoyu (6), our (5), available (5), the (5), data (5), extraction (5), github (4), copyright (4), for (4), models (4), quality (4), nicholas (4), may (3), diffusion (3), accepted (3), 2024 (3), new (3), arxiv (3), generative (3), follow (2), adversarial (2), project (2), mist (2), 2023 (2), has (2), been (2), protection (2), against (2), attacks (2), paper (2), authentication (2), image (2), using (2), work (2), training (2), was (2), high (2), volunteer (2), email (2), interested (2), modeling (2), 吴晓宇 (2), scholar (2), powered, fork, site, last, updated, minimal, mistakes, academicpages, jekyll, feed, sitemap, watermarking, now, add, watermarks, protect, your, artwork, from, unauthorized, use, open, source, released, provides, enhanced, lora, based, more, details, are, homepage, dec, cvpr, read, full, code, through, revelio, cvf, feb, published, findings, mitigating, degradation, during, few, shot, fine, tuning, identified, phenomenon, called, corruption, stage, where, abnormally, degrades, improved, performance, bnns, personalized, demonstrate, publicly, checkpoints, hugging, face, icml, show, that, even, when, model, can, still, leak, removed, enabling, practice, under, realistic, real, world, deployments, exactly, unlearned, neurips, after, exact, unlearning, sep, news, founded, interest, group, focused, issues, related, develop, software, provide, technical, support, litigation, basis, feel, free, you, need, assistance, also, currently, working, with, prof, chen, wei, research, interests, include, personalization, well, privacy, security, topics, such, defenses, membership, inference, semantic, google, rice, university, phd, student, trustworthy, cat, publications,

Text of the page (random words):
xiaoyu nicholas wu 吴晓宇 xiaoyu nicholas wu xiaoyu nicholas wu publications cv cat xiaoyu wu phd student in cs trustworthy ai generative modeling follow us rice university email google scholar semantic scholar github xiaoyu nicholas wu 吴晓宇 my research interests include copyright protection and authentication for and against ai personalization as well as privacy and security topics such as adversarial attacks and defenses data extraction and membership inference i m also interested in generative modeling and am currently working with prof chen wei i co founded a volunteer interest group focused on copyright issues related to image generative models we develop software and provide technical support for ai copyright litigation on a volunteer basis feel free to email us if you re interested or need assistance news sep 2025 our new work on data extraction after exact unlearning was accepted to neurips 2025 and is available on arxiv we show that even when a model is exactly unlearned it can still leak the removed data under realistic real world deployments enabling high quality extraction in practice may 2025 our new work on training data extraction for personalized diffusion models was accepted to icml 2025 and is available on arxiv we demonstrate high quality training data extraction using publicly available checkpoints on hugging face may 2024 published new findings on mitigating quality degradation during few shot fine tuning of diffusion models arxiv we identified a phenomenon called the corruption stage where image quality abnormally degrades and improved performance using bnns feb 2024 our paper on copyright authentication for diffusion models has been accepted at cvpr 2024 read the full paper on cvf the code is available through our project revelio on github dec 2023 mist v2 has been released it provides enhanced protection against lora based attacks more details are available on the homepage may 2023 our adversarial watermarking project mist is now open source on github add watermarks to protect your artwork from unauthorized use sitemap follow github feed 2025 xiaoyu wu powered by jekyll academicpages a fork of minimal mistakes site last updated 2025 12 23