Výsledky vyhledávání

Report

SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark

Autor: Niu, Jun, Zhu, Xiaoyan, Zeng, Moxuan, Zhang, Ge, Zhao, Qingyang, Huang, Chunhui, Zhang, Yangming, An, Suyu, Wang, Yangzhong, Yue, Xinghui, He, Zhipeng, Guo, Weihao, Shen, Kuo, Liu, Peng, Shen, Yulong, Jiang, Xiaohong, Ma, Jianfeng, Zhang, Yuqing

Membership inference (MI) attacks threaten user privacy through determining if a given data example has been used to train a target model. However, it has been increasingly recognized that the "comparing different MI attacks" methodology used in the

Externí odkaz: http://arxiv.org/abs/2307.06123

Zobrazit plný text záznamu

Report

Robust Deep Compressive Sensing with Recurrent-Residual Structural Constraints

Autor: Niu, Jun

Existing deep compressive sensing (CS) methods either ignore adaptive online optimization or depend on costly iterative optimizer during reconstruction. This work explores a novel image CS framework with recurrent-residual structural constraint, term

Externí odkaz: http://arxiv.org/abs/2207.07301

Zobrazit plný text záznamu