{
  "id": "1911.10291",
  "version": "v1",
  "published": "2019-11-23T01:15:32.000Z",
  "updated": "2019-11-23T01:15:32.000Z",
  "title": "Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference",
  "authors": [
    "Wei-An Lin",
    "Yogesh Balaji",
    "Pouya Samangouei",
    "Rama Chellappa"
  ],
  "categories": [
    "cs.CV"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-11-23T01:15:32.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "generative adversarial networks",
      "model-based approximate inversion",
      "secure inference",
      "projection-based defense mechanism",
      "implement reparameterization white-box attacks"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}