IEEE 3304-2023 PDF

IEEE 3304-2023 PDF

The Neural Network Watermarking (MPAI-NNW) Technical Specification provides standard methods to measure the ability of 1) a watermark inserter to inject a payload without deteriorating the neural network (NN) performance, 2) a watermark detector to recognize the presence and the watermark decoder to successfully retrieve the payload of the inserted watermark, and 3) a watermark inserter to inject a payload and the watermark detector/decoder to detect/decode a payload from a watermarked model or from any of its inferences at a measured computational cost.
New IEEE Standard – Active. This is an adoption of the Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI)–Technical Specification Neural Network Watermarking as an IEEE Standard. The Neural Network Watermarking (MPAI-NNW) Technical Specification provides standard methods to measure the ability of 1) a watermark inserter to inject a payload without deteriorating the neural network (NN) performance, 2) a watermark detector to recognize the presence and the watermark decoder to successfully retrieve the payload of the inserted watermark, and 3) a watermark inserter to inject a payload and the watermark detector/decoder to detect/decode a payload from a watermarked model or any of its inferences at a measured computational cost.