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 the 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

On Utility and Privacy in Synthetic Genomic Data

Bristena Oprisanu (UCL), Georgi Ganev (UCL & Hazy), Emiliano De Cristofaro (UCL)

Read More

FakeGuard: Exploring Haptic Response to Mitigate the Vulnerability in...

Aditya Singh Rathore (University at Buffalo, SUNY), Yijie Shen (Zhejiang University), Chenhan Xu (University at Buffalo, SUNY), Jacob Snyderman (University at Buffalo, SUNY), Jinsong Han (Zhejiang University), Fan Zhang (Zhejiang University), Zhengxiong Li (University of Colorado Denver), Feng Lin (Zhejiang University), Wenyao Xu (University at Buffalo, SUNY), Kui Ren (Zhejiang University)

Read More

Transparency Dictionaries with Succinct Proofs of Correct Operation

Ioanna Tzialla (New York University), Abhiram Kothapalli (Carnegie Mellon University), Bryan Parno (Carnegie Mellon University), Srinath Setty (Microsoft Research)

Read More

Trust and Privacy Expectations during Perilous Times of Contact...

Habiba Farzand (University of Glasgow), Florian Mathis (University of Glasgow), Karola Marky (University of Glasgow), Mohamed Khamis (University of Glasgow)

Read More