Digital, Semantic and Physical Analysis of Media Integrity (DiSPARITY)


Sponsored by DARPA’s MediFor program, DiSPARITY develops deep learning algorithms for identifying digital, physical, and semantic image and video manipulations. Image manipulations include image splicing, copy-move, and image repurposing. DiSPARITY also develops robust, subject-agnostic machine learning methods and systems for deepfake detection.


Collaborating Institutions


June, 2019

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

The matching problem is a basic problem in computer vision. There are region-based matching problems, such as template matching, and semantic-based matching problems, such as semantic alignment. In this work, we will first go through classic solutions for template matching. Then we demonstrate our deep learning-friendly matching algorithm QATM and its performance on template matching in a training-free way (only use pre-trained model weights, no other training involved). Finally, we implement QATM as a learning DNN module and show its applications in semantic matching problems (e.g. semantic alignment).

June, 2019

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Fake news, Internet rumors, insurance fraud, extortion, and even academic publications have all been affected by image forgery, which has recently become an epidemic. Furthermore, the majority of image forgeries have yet to be recognized. Each of the retracted articles due to deliberate manipulation might account for a mean of $392,582 indirect expenses in biomedical research publications alone, implying much larger indirect costs due to misguided research. As a result, new algorithms must be developed to aid in the fight against image manipulation and forgery.

September, 2018

Neural Information Processing Systems (NIPS)

Representation learning is a key ingredient for machine learning algorithms and its effectiveness and efficiency has a direct correlation to performance of an algorithm. Supervised algorithms involve learning a mapping from a data sample x to a target variable y by estimating a conditional probability p(y|x) from the data. In the real world, often the data sample x is itself composed of many nuisance factors and noises that are irrelevant to the prediction of y and could lead to overfitting of the model. For example, a nuisance factor in the case of face recognition is images is the lighting condition the photograph was captured in, and a recognition model that associates lighting with subject identity is expected to perform poorly.


Defense Advanced Research Project Agency