Towards Model Robustness And Generalization Against Adversarial Examples For Deep Neural Networks

Towards Model Robustness and Generalization Against Adversarial Examples for Deep Neural Networks

Proceedings of the 6th International Conference on Deep Learning, Artificial Intelligence and Robotics (ICDLAIR 2024)

This is an open access book. The proposed conference ICDLAIR 2024 represents key ingredients for the 5G. The extensive application of AI and DL is dramatically changing products and services, with a large impact on labour, economy and society at all. ICDLAIR 2024, organized by NIT Kurukshetra, India in collaboration with International Association of Academicians (IAASSE), Emlyon Business School France and CSUSB USA, aims at collecting scientific and technical contributions with respect to models, tools, technologies and applications in the field of modern artificial intelligence and robotics, covering the entire range of concepts from theory to practice, including case studies, works-in-progress, and conceptual explorations. Through sharing and networking, ICDLAIR 2024 will provide an opportunity for researchers, practitioners and educators to exchange research evidence, practical experiences and innovative ideas on issues related to the Conference theme. ICDLAIR 2024 intends to publish the post-conference work in order to give authors the opportunity to collect feedback during the presentation.

Malware Detection

This book captures the state of the art research in the area of malicious code detection, prevention and mitigation. It contains cutting-edge behavior-based techniques to analyze and detect obfuscated malware. The book analyzes current trends in malware activity online, including botnets and malicious code for profit, and it proposes effective models for detection and prevention of attacks using. Furthermore, the book introduces novel techniques for creating services that protect their own integrity and safety, plus the data they manage.