[D-20] Enriched Multimedia

4:15 PM - 4:30 PM JST(7:15 AM - 7:30 AM UTC)Candidate for Academic Incentive Award

[D-20-02] A Method of Model Inversion Attacks on Pre-trained Face Encoders

◎Tomoshi Matsuyama¹, Kazuaki Nakamura ¹ (1. Tokyo Univ. of Science)

Keywords:

model inversion attacks,face encoder,conditional diffusion models