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

Tetrad: Actively Secure 4PC for Secure Training and Inference

Nishat Koti (IISc Bangalore), Arpita Patra (IISc Bangalore), Rahul Rachuri (Aarhus University, Denmark), Ajith Suresh (IISc, Bangalore)

Read More

HeadStart: Efficiently Verifiable and Low-Latency Participatory Randomness Generation at...

Hsun Lee (National Taiwan University), Yuming Hsu (National Taiwan University), Jing-Jie Wang (National Taiwan University), Hao Cheng Yang (National Taiwan University), Yu-Heng Chen (National Taiwan University), Yih-Chun Hu (University of Illinois at Urbana-Champaign), Hsu-Chun Hsiao (National Taiwan University)

Read More

SpiralSpy: Exploring a Stealthy and Practical Covert Channel to...

Zhengxiong Li (University at Buffalo, SUNY), Baicheng Chen (University at Buffalo), Xingyu Chen (University at Buffalo), Huining Li (SUNY University at Buffalo), Chenhan Xu (University at Buffalo, SUNY), Feng Lin (Zhejiang University), Chris Xiaoxuan Lu (University of Edinburgh), Kui Ren (Zhejiang University), Wenyao Xu (SUNY Buffalo)

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