Convert Apple NeuralHash model for CSAM Detection to ONNX

Re:Convert Apple NeuralHash model for CSAM Detection to ONNX by heavyset_go on Wednesday August 18, 2021 @02:15PM (#28225063)

Perceptual hashing systems that do derivative image lookups don't rely on exact hash comparisons, but fuzzy hash comparisons using a distance metric like the Hamming distance to find similar images.

If two hashes are off by a bit or two, chances are that the two images are derived from the same, or similar, source image.

[ Parent | on HN ]

Re:Convert Apple NeuralHash model for CSAM Detection to ONNX by toxik on Wednesday August 18, 2021 @04:53PM (#28226992)

I can restate what I said again for you: I can generate noise that makes the Hamming distance or whatever metric you prefer arbitrarily large without changing the contents noticeably.

[ Parent | on HN ]