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.
MIRROR: Model Inversion for Deep LearningNetwork with High Fidelity
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)
View More Papers
Evaluating Susceptibility of VPN Implementations to DoS Attacks Using...
Fabio Streun (ETH Zurich), Joel Wanner (ETH Zurich), Adrian Perrig (ETH Zurich)
Read MoreDemo #2: Policy-based Discovery and Patching of Logic Bugs...
Hyungsub Kim (Purdue University), Muslum Ozgur Ozmen (Purdue University), Antonio Bianchi (Purdue University), Z. Berkay Celik (Purdue University) and Dongyan...
Read MoreKasper: Scanning for Generalized Transient Execution Gadgets in the...
Brian Johannesmeyer (VU Amsterdam), Jakob Koschel (VU Amsterdam), Kaveh Razavi (ETH Zurich), Herbert Bos (VU Amsterdam), Cristiano Giuffrida (VU Amsterdam)
Read MoreDetecting CAN Masquerade Attacks with Signal Clustering Similarity
Pablo Moriano (Oak Ridge National Laboratory), Robert A. Bridges (Oak Ridge National Laboratory) and Michael D. Iannacone (Oak Ridge National...
Read More