Quantifying the Cost of Reliable Photo Authentication via High-Performance Learned Lossy RepresentationsDownload PDF

25 Sept 2019, 19:19 (modified: 11 Mar 2020, 07:34)ICLR 2020 Conference Blind SubmissionReaders: Everyone
Original Pdf: pdf
Code: https://github.com/pkorus/neural-imaging
Keywords: image forensics, photo manipulation detection, learned compression, lossy compression, image compression, entropy estimation
TL;DR: We learn an efficient lossy image codec that can be optimized to facilitate reliable photo manipulation detection at fractional cost in payload/quality and even at low bitrates.
Abstract: Detection of photo manipulation relies on subtle statistical traces, notoriously removed by aggressive lossy compression employed online. We demonstrate that end-to-end modeling of complex photo dissemination channels allows for codec optimization with explicit provenance objectives. We design a lightweight trainable lossy image codec, that delivers competitive rate-distortion performance, on par with best hand-engineered alternatives, but has lower computational footprint on modern GPU-enabled platforms. Our results show that significant improvements in manipulation detection accuracy are possible at fractional costs in bandwidth/storage. Our codec improved the accuracy from 37% to 86% even at very low bit-rates, well below the practicality of JPEG (QF 20).
7 Replies