Shengwei An (Purdue University), Guanhong Tao (Purdue University), Qiuling Xu (Purdue University), Yingqi Liu (Purdue University), Guangyu Shen (Purdue University), Yuan Yao (Nanjing University), Jingwei Xu (Nanjing University), Xiangyu Zhang (Purdue University)

Model inversion reverse-engineers input samples from a given model, and hence poses serious threats to information confidentiality. We propose a novel inversion technique based on StyleGAN, whose generator has a special architecture that forces the decomposition of an input to styles of various granularities such that the model can learn them separately in training. During sample generation, the generator transforms a latent value to parameters controlling these styles to compose a sample. In our inversion, given a target label of some subject model to invert (e.g., a private face based identity recognition model), our technique leverages a StyleGAN trained on public data from the same domain (e.g., a public human face dataset), uses gradient descent or genetic search algorithm, together with distribution based clipping, to find a proper parameterization of the styles such that the generated sample is correctly classified to the target label (by the subject model) and recognized by humans. The results show that our inverted samples have high fidelity, substantially better than those by existing state-of-the-art techniques.

View More Papers

PHYjacking: Physical Input Hijacking for Zero-Permission Authorization Attacks on...

Xianbo Wang (The Chinese University of Hong Kong), Shangcheng Shi (The Chinese University of Hong Kong), Yikang Chen (The Chinese University of Hong Kong), Wing Cheong Lau (The Chinese University of Hong Kong)

Read More

Problematic Content in Online Ads

Franzisca Roesner (University of Washington)

Read More

COOPER: Testing the Binding Code of Scripting Languages with...

Peng Xu (TCA/SKLCS, Institute of Software, Chinese Academy of Sciences; University of Chinese Academy of Sciences), Yanhao Wang (QI-ANXIN Technology Research Institute), Hong Hu (Pennsylvania State University), Purui Su (TCA/SKLCS, Institute of Software, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences)

Read More