PDQ & TMK + PDQF -- A Test Drive of Facebook's Perceptual Hashing Algorithms
This work addresses the challenge of automated detection of modified multimedia files for law enforcement, though it is incremental as it applies existing algorithms to new data.
The researchers tested Facebook's open-sourced PDQ and TMK + PDQF perceptual hashing algorithms on real-world law enforcement data to detect modified images and videos, finding they effectively handle common transformations.
Efficient and reliable automated detection of modified image and multimedia files has long been a challenge for law enforcement, compounded by the harm caused by repeated exposure to psychologically harmful materials. In August 2019 Facebook open-sourced their PDQ and TMK + PDQF algorithms for image and video similarity measurement, respectively. In this report, we review the algorithms' performance on detecting commonly encountered transformations on real-world case data, sourced from contemporary investigations. We also provide a reference implementation to demonstrate the potential application and integration of such algorithms within existing law enforcement systems.