Fighting Fake News: Image Splice Detection via Learned Self-Consistency

Minyoung Huh, Andrew Liu, Andrew Owens and Alexei (Alyosha) Efros

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2018-67
May 14, 2018

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-67.pdf

Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient training data. In this paper, we propose a model that learns to detect visual manipulations from unlabeled data through self-supervision. Given a large collection of real photographs with automatically recorded EXIF metadata, we train a model to determine whether an image is self-consistent — that is, whether its content could have been produced by a single imaging pipeline. We apply this self-supervised learning method to the task of detecting and localizing image splices. Although the proposed model obtains state-of-the-art performance on several benchmarks, we see it as merely a step in the long quest for a truly general-purpose visual forensics tool.


BibTeX citation:

@techreport{Huh:EECS-2018-67,
    Author = {Huh, Minyoung and Liu, Andrew and Owens, Andrew and Efros, Alexei (Alyosha)},
    Title = {Fighting Fake News: Image Splice Detection via Learned Self-Consistency},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2018},
    Month = {May},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-67.html},
    Number = {UCB/EECS-2018-67},
    Abstract = {Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient training data. In this paper, we propose a model that learns to detect visual manipulations from unlabeled data through self-supervision. Given a large collection of real photographs with automatically recorded EXIF metadata, we train a model to determine whether an image is self-consistent — that is, whether its content could have been produced by a single imaging pipeline. We apply this self-supervised learning method to the task of detecting and localizing image splices. Although the proposed model obtains state-of-the-art performance on several benchmarks, we see it as merely a step in the long quest for a truly general-purpose visual forensics tool.}
}

EndNote citation:

%0 Report
%A Huh, Minyoung
%A Liu, Andrew
%A Owens, Andrew
%A Efros, Alexei (Alyosha)
%T Fighting Fake News: Image Splice Detection via Learned Self-Consistency
%I EECS Department, University of California, Berkeley
%D 2018
%8 May 14
%@ UCB/EECS-2018-67
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-67.html
%F Huh:EECS-2018-67