LEADER 04475nam 22006735 450 001 996546839603316 005 20230529115623.0 010 $a981-19-7554-X 024 7 $a10.1007/978-981-19-7554-7 035 $a(MiAaPQ)EBC30554450 035 $a(Au-PeEL)EBL30554450 035 $a(DE-He213)978-981-19-7554-7 035 $a(BIP)085784258 035 $a(PPN)270617817 035 $a(EXLCZ)9926801504100041 100 $a20230529d2023 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aDigital Watermarking for Machine Learning Model$b[electronic resource] $eTechniques, Protocols and Applications /$fedited by Lixin Fan, Chee Seng Chan, Qiang Yang 205 $a1st ed. 2023. 210 1$aSingapore :$cSpringer Nature Singapore :$cImprint: Springer,$d2023. 215 $a1 online resource (233 pages) 311 08$aPrint version: Fan, Lixin Digital Watermarking for Machine Learning Model Singapore : Springer Singapore Pte. Limited,c2023 9789811975530 327 $aPart I. Preliminary -- Chapter 1. Introduction -- Chapter 2. Ownership Verification Protocols for Deep Neural Network Watermarks -- Part II Techniques -- Chapter 3. ModelWatermarking for Image Recovery DNNs -- Chapter 4. The Robust and Harmless ModelWatermarking -- Chapter 5. Protecting Intellectual Property of Machine Learning Models via Fingerprinting the Classification Boundary -- Chapter 6. Protecting Image Processing Networks via Model Water -- Chapter 7. Watermarks for Deep Reinforcement Learning -- Chapter 8. Ownership Protection for Image Captioning Models -- Chapter 9.Protecting Recurrent Neural Network by Embedding Key -- Part III Applications -- Chapter 10. FedIPR: Ownership Verification for Federated Deep Neural Network Models -- Chapter 11. Model Auditing For Data Intellectual Property . 330 $aMachine learning (ML) models, especially large pretrained deep learning (DL) models, are of high economic value and must be properly protected with regard to intellectual property rights (IPR). Model watermarking methods are proposed to embed watermarks into the target model, so that, in the event it is stolen, the model?s owner can extract the pre-defined watermarks to assert ownership. Model watermarking methods adopt frequently used techniques like backdoor training, multi-task learning, decision boundary analysis etc. to generate secret conditions that constitute model watermarks or fingerprints only known to model owners. These methods have little or no effect on model performance, which makes them applicable to a wide variety of contexts. In terms of robustness, embedded watermarks must be robustly detectable against varying adversarial attacks that attempt to remove the watermarks. The efficacy of model watermarking methods is showcased in diverse applications including image classification, image generation, image captions, natural language processing and reinforcement learning. This book covers the motivations, fundamentals, techniques and protocols for protecting ML models using watermarking. Furthermore, it showcases cutting-edge work in e.g. model watermarking, signature and passport embedding and their use cases in distributed federated learning settings. 606 $aMachine learning 606 $aData protection 606 $aImage processing?Digital techniques 606 $aComputer vision 606 $aImage processing 606 $aMachine Learning 606 $aData and Information Security 606 $aComputer Imaging, Vision, Pattern Recognition and Graphics 606 $aImage Processing 610 $aEngineering 610 $aTechnology & Engineering 615 0$aMachine learning. 615 0$aData protection. 615 0$aImage processing?Digital techniques. 615 0$aComputer vision. 615 0$aImage processing. 615 14$aMachine Learning. 615 24$aData and Information Security. 615 24$aComputer Imaging, Vision, Pattern Recognition and Graphics. 615 24$aImage Processing. 676 $a005.82 700 $aFan$b Lixin$01362784 701 $aChan$b Chee Seng$01362785 701 $aYang$b Qiang$0867534 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a996546839603316 996 $aDigital Watermarking for Machine Learning Model$93382324 997 $aUNISA