Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Chong, Baoli"'
Autor:
Fang, Hao, Qiu, Yixiang, Yu, Hongyao, Yu, Wenbo, Kong, Jiawei, Chong, Baoli, Chen, Bin, Wang, Xuan, Xia, Shu-Tao
Model Inversion (MI) attacks aim to disclose private information about the training data by abusing access to the pre-trained models. These attacks enable adversaries to reconstruct high-fidelity data that closely aligns with the private training dat
Externí odkaz:
http://arxiv.org/abs/2402.04013