Artificial Intelligence Data and Model Safety: Risks, Attacks and Defenses offers a comprehensive overview of the evolution of AI and its security concerns. The book delves into how historical advancements in AI have both bolstered and complicated the issue of safeguarding data and models. By reflecting on the interplay between machine learning innovations and vulnerabilities, it sets the stage for readers to understand the critical importance of robust defenses in this era of digital and ...

This book provides an overview of the recent advances in representation learning theory, algorithms, and applications for natural language processing (NLP), ranging from word embeddings to pre-trained language models. It is divided into four parts. Part I presents the representation learning techniques for multiple language entries, including words, sentences and documents, as well as pre-training techniques. Part II then introduces the related representation techniques to NLP, including g...

This open access book systematically investigates the topic of entity alignment, which aims to detect equivalent entities that are located in different knowledge graphs. Entity alignment represents an essential step in enhancing the quality of knowledge graphs, and hence is of significance to downstream applications, e.g., question answering and recommender systems. Recent years have witnessed a rapid increase in the number of entity alignment frameworks, while the relationships among them...

Comprehensive overview of the principles, theories, and techniques needed to build end-to-end semantic communication systems, with case studies included.In this rapidly evolving landscape, the integration of connected intelligence applications highlights the pressing need for networks to gain intelligence in a non-siloed and ad hoc manner. The traditional incremental approach to network design is no longer sufficient to support the diverse and dynamic requirements ...

Transfer learning is one of the most important technologies in the era of artificial intelligence and deep learning. It seeks to leverage existing knowledge by transferring it to another, new domain. Over the years, a number of relevant topics have attracted the interest of the research and application community: transfer learning, pre-training and fine-tuning, domain adaptation, domain generalization, and meta-learning.This book offers a comprehensive tutorial on an overview of tr...

Deep learning systems have gotten really great at identifying patterns in text, images, and video. But applications that create realistic images, natural sentences and paragraphs, or native-quality translations have proven elusive. Generative Adversarial Networks, or GANs, offer a promising solution to these challenges by pairing two competing neural networks' one that generates content and the other that rejects samples that are of poor quality.GANs in Action: Deep learning wi...

Adversarial Robustness for Machine Learning summarizes the recent progress on this topic and introduces popular algorithms on adversarial attack, defense and verification. Sections cover adversarial attack, verification and defense, mainly focusing on image classification applications which are the standard benchmark considered in the adversarial robustness community. Other sections discuss adversarial examples beyond image classification, other threat models beyond testing time attack, and a...

This four-volume set LNCS 16053-16056 constitutes the refereed proceedings of the 30th European Symposium on Research in Computer Security, ESORICS 2025, held in Toulouse, France, during September 22–24, 2025.The 100 full papers presented in these proceedings were carefully reviewed and selected from 600 submissions. They were organized in topical sections as follows:AI and Data-Centric Security, Systems and Hardware Security, Privacy, Cryptography and Secure Protocol Desig...

This 15-volume set LNCS 15031-15045 constitutes the refereed proceedings of the 7th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2024, held in Urumqi, China, during October 18–20, 2024.The 579 full papers presented were carefully reviewed and selected from 1526 submissions. The papers cover various topics in the broad areas of pattern recognition and computer vision, including machine learning, pattern classification and cluster analysis, neural network and de...

This is the first textbook focusing on practicality of machine learning (ML) and deep neural networks (DNN), by introducing methods that enable engineering applications of ML and DNN models. The authors describe many methodologies that are widely used in designing, training, and deploying of these models and discuss their applicability under various contexts. Coverage begins with the basic knowledge of machine learning and deep neural networks and their applications in solving practical en...

The multi-volume set of LNCS books with volume numbers 15301-15333 constitutes the refereed proceedings of the 27th International Conference on Pattern Recognition, ICPR 2024, held in Kolkata, India, during December 1–5, 2024.The 963 papers presented in these proceedings were carefully reviewed and selected from a total of 2106 submissions. They deal with topics such as Pattern Recognition; Artificial Intelligence; Machine Learning; Computer Vision; Robot Vision; Machine Vision; Im...

This book introduces a new type of data poisoning attack, dubbed, backdoor attack. In backdoor attacks, an attacker can train the model with poisoned data to obtain a model that performs well on a normal input but behaves wrongly with crafted triggers. Backdoor attacks can occur in many scenarios where the training process is not entirely controlled, such as using third-party datasets, third-party platforms for training, or directly calling models provided by third parties. Due to the enor...