This book presents applications of innovative techniques for studying and solving complex problems in artificial intelligence and computing. This edition brings together experience, current work, and promising future trends related to distributed computing, artificial intelligence, and their applications to provide efficient solutions to real-world problems. Given the conference's success, this edition features twelve special sessions covering a wide range of topics related to AI and other areas of interest. These sessions were carefully curated to address the latest advancements and challenges in fields such as machine learning, neural networks, IoT, big data, and blockchain, among others. The accepted papers from these sessions are presented in two volumes, showcasing the diverse and innovative research being conducted in these domains. This is the first volume, which includes the sessions: Artificial intelligence for enhanced cyber security (AI4CS), AI-driven methods for multimodal networks and processes modeling (AIMPM), computational linguistics, information, reasoning, and AI (CLIRAI), novel technologies for smart industry and mobility (SmartMob), intelligent Internet of things security and privacy (WISP) and revolutionizing carbon farming by nature-based business models and emerging innovations in the field of artificial intelligence, satellite and green technologies (INNO4CFIS), each focusing on specific themes within the broader scope of AI and its applications. The DCAI'24 technical program has selected 74 papers in special sessions and, as in past editions, it will be special issues in ranked journals. This symposium is organized by the University of Salamanca (Spain). The authors would like to thank all the contributing authors, the program committee members, national associations (AEPIA, APPIA, LASI), and the sponsors (AIR Institute).
Efficient Network Traffic Feature Sets for IoT Intrusion Detection.- Adversarial Evasion Attack Efficiency against Large Language Models.- ModSec-Learn: Boosting ModSecurity with Machine Learning.- SCoPE: Evaluating LLMs for Software Vulnerability Detection, etc.
