Mislgan: An Anti-Forensic Camera Model Falsification Framework Using A Generative Adversarial Network

Chen Chen, Xinwei Zhao, Matthew C. StammICIP 2018 · OpenReview

Abstract

Deep learning techniques have become popular for performing camera model identification. To expose weaknesses in these methods, we propose a new anti-forensic framework that utilizes a generative adversarial network (GAN) to falsify an image's source camera model. Our proposed attack uses the generator trained in the GAN to produce an image that can fool a CNN-based camera model identification classifier. Moreover, our proposed attack will only introduce a minimal amount of distortion to the falsified image that is not perceptible to human eyes. By conducting experiments on a large amount of data, we show that the proposed attack can successfully fool a state-of-art camera model identification CNN classifier with 98% probability and maintain high image quality.
BibTeX
@inproceedings{chen2018mislgan,
  author = {Chen Chen and Xinwei Zhao and Matthew C. Stamm},
  title = {{Mislgan: An Anti-Forensic Camera Model Falsification Framework Using A Generative Adversarial Network}},
  booktitle = {ICIP},
  year = {2018},
  url = {https://openreview.net/forum?id=JYRcWuj57nT},
}

Loading related content...

Figure