Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference

November 23, 2019 ยท Entered Twilight ยท ๐Ÿ› arXiv.org

๐ŸŒ… TWILIGHT: Old Age
Predates the code-sharing era โ€” a pioneer of its time

"Last commit was 6.0 years ago (โ‰ฅ5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, _init_paths.py, blackbox.py, classification.py, classifiers, cleverhans, comparison, datasets, debug.py, download_dataset.py, evaluate.py, experiments, figures, models, mse_roc_classification.py, plots, requirements.txt, setup.sh, tflib, train.py, train_cgan.py, utils, whitebox.py, whitebox_cifar.py

Authors Wei-An Lin, Yogesh Balaji, Pouya Samangouei, Rama Chellappa arXiv ID 1911.10291 Category cs.LG: Machine Learning Cross-listed cs.CV, stat.ML Citations 7 Venue arXiv.org Repository https://github.com/yogeshbalaji/InvGAN โญ 15 Last Checked 1 month ago
Abstract
Inferring the latent variable generating a given test sample is a challenging problem in Generative Adversarial Networks (GANs). In this paper, we propose InvGAN - a novel framework for solving the inference problem in GANs, which involves training an encoder network capable of inverting a pre-trained generator network without access to any training data. Under mild assumptions, we theoretically show that using InvGAN, we can approximately invert the generations of any latent code of a trained GAN model. Furthermore, we empirically demonstrate the superiority of our inference scheme by quantitative and qualitative comparisons with other methods that perform a similar task. We also show the effectiveness of our framework in the problem of adversarial defenses where InvGAN can successfully be used as a projection-based defense mechanism. Additionally, we show how InvGAN can be used to implement reparameterization white-box attacks on projection-based defense mechanisms. Experimental validation on several benchmark datasets demonstrate the efficacy of our method in achieving improved performance on several white-box and black-box attacks. Our code is available at https://github.com/yogeshbalaji/InvGAN.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning