Fawkes: Protecting Privacy against Unauthorized Deep Learning Models

By Shawn Shan, Emily Wenger, Jiayun Zhang, Huiying Li, Haitao Zheng, Ben Y. Zhao. USENIX Security Symposium, 2020

307 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/755a392fe813c9ba3282f60c0e1f1ec81e68f263

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Shawn Shan
2. Ayush Kumar Tarun
3. Jenna Cryan
4. Yisroel Mirsky
5. Emily Wenger
6. Haitao Zheng
7. Vikram S Chundawat
8. Ben Y. Zhao

Citations in the corpus

• GLAZE: Protecting Artists from Style Mimicry by Text-to-Image Models (2023, methodology): “For the target image used, we assume Fawkes randomly picks an artwork from a different artist.”
• The Creation and Detection of Deepfakes (2020, background): “In a di‚erent approach, the authors of [138] use adversarial noise to change the identity of the face so that web crawlers will not be able €nd the image of t to train their model.”
• Fast Yet Effective Machine Unlearning (2021, background): “Another privacy setting [25, 40] consider a scenario where the goal is to make the personal data completely unusable for unauthorized deep learning models.”