Kirjahaku

The widespread use of image, audio, and video data makes media content protection increasingly necessary and urgent. For maximum safety, it is no longer sufficient to merely control access rights. In order to fully protect multimedia data from piracy or unauthorized use, it must be secured through encryption prior to its transmission or distribution. Multimedia Content Encryption: Techniques and Applications presents the latest research results in this dynamic field. The book begins with the history of multimedia encryption and then examines general performance requirements of encryption and fundamental encrypting techniques. It discusses common techniques of complete, partial, and compression-combined encryption; as well as the more specialized forms, including perception, scalable, and commutative encryption. In addition, the author reviews watermarking and joint fingerprint embedding and decryption. Later chapters discuss typical attacks on multimedia encryption, as well as the principles for designing secure algorithms and various applications. An exploration of open issues, up-and-coming topics, and areas for further research rounds out the coverage. Shiguo Lian is the author or co-author of more than fifty peer-reviewed journal and conference articles covering topics of network security and multimedia content protection, including cryptography, secure P2P content sharing, digital rights management (DRM), encryption, watermarking, digital fingerprinting, and authentication. By following the techniques outlined in this book, users will be better able to protect the integrity of their multimedia data and develop greater confidence that their data will not be misappropriated.

This book proposes practical application paradigms for deep neural networks, aiming to establish best practices for real-world implementation.Over the past decade, deep neural networks have made significant progress. However, effectively applying these networks to solve various practical problems remains challenging, which has limited the widespread application of artificial intelligence. Artificial Intelligence Paradigms for Application Practice is the first to comprehensively address implementation paradigms for deep neural networks in practice. The authors begin by reviewing the development of artificial neural networks and provide a systematic introduction to the tasks, principles, and architectures of deep neural networks. They identify the practical limitations of deep neural networks and propose guidelines and strategies for successful implementation. The book then examines 14 representative applications in urban planning, industrial production, and transportation. For each case, the authors present a landing paradigm that effectively addresses practical challenges supported by illustrations, background information, related work, methods, experiments, and conclusions. The experimental results validate the effectiveness of the proposed implementation approaches.The book will benefit researchers, engineers, undergraduate, and graduate students interested in artificial intelligence, deep neural networks, large models, stable diffusion models, video surveillance, smart cities, intelligent manufacturing, intelligent transportation, and other related areas.