IEEE Standard for Adoption of Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) Technical Specification Neural Network Watermarking (NNW) V1
IEEE Std 3304-2023
Year: 2024
IEEE - The Institute of Electrical and Electronics Engineers, Inc.
Abstract: 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.
Subject: Neural Network Watermarking
-
Statistics
IEEE Standard for Adoption of Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) Technical Specification Neural Network Watermarking (NNW) V1
Show full item record
contributor author | IEEE - The Institute of Electrical and Electronics Engineers, Inc. | |
date accessioned | 2024-12-17T08:46:51Z | |
date available | 2024-12-17T08:46:51Z | |
date copyright | 12 February 2024 | |
date issued | 2024 | |
identifier other | 10431696.pdf | |
identifier uri | http://yse.yabesh.ir/std;jsessionid=A33FFBB4A04818B251172099FA6814F7/handle/yse/336431 | |
description abstract | 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. | |
language | English | |
publisher | IEEE - The Institute of Electrical and Electronics Engineers, Inc. | |
title | IEEE Standard for Adoption of Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) Technical Specification Neural Network Watermarking (NNW) V1 | en |
title | IEEE Std 3304-2023 | num |
type | standard | |
page | 26 | |
tree | IEEE - The Institute of Electrical and Electronics Engineers, Inc.:;2024 | |
contenttype | fulltext | |
subject keywords | Neural Network Watermarking | |
subject keywords | AI framework | |
subject keywords | MPAI-NNW | |
subject keywords | IEEE 3304™ | |
subject keywords | Artificial Intelligence | |
subject keywords | adoption | |
identifier DOI | 10.1109/IEEESTD.2024.10431696 |