First to Possess His Statistics: Data-Free Model Extraction Attack on Tabular Data

no code implementations • 30 Sep 2021 • Masataka Tasumi, Kazuki Iwahana, Naoto Yanai, Katsunari Shishido, Toshiya Shimizu, Yuji Higuchi, Ikuya Morikawa, Jun Yajima

Whereas model extraction is more challenging on tabular data due to normalization, TEMPEST no longer needs initial samples that previous attacks require; instead, it makes use of publicly available statistics to generate query samples.

Medical Diagnosis Model extraction