Huang, Xiaowei creator author. Jin, Gaojie author. Ruan, Wenjie author. text bibliography si 2023 monographic eng

print

xvii, 321 pages : illustrations ; 24 cm. " Machine learning algorithms allow computers to learn without being explicitly programmed. Their application is now spreading to highly sophisticated tasks across multiple domains, such as medical diagnostics or fully autonomous vehicles. While this development holds great potential, it also raises new safety concerns, as machine learning has many specificities that make its behaviour prediction and assessment very different from that for explicitly programmed software systems. This book addresses the main safety concerns with regard to machine learning, including its susceptibility to environmental noise and adversarial attacks. Such vulnerabilities have become a major roadblock to the deployment of machine learning in safety-critical applications. The book presents up-to-date techniques for adversarial attacks, which are used to assess the vulnerabilities of machine learning models; formal verification, which is used to determine if a trained machine learning model is free of vulnerabilities; and adversarial training, which is used to enhance the training process and reduce vulnerabilities. The book aims to improve readers’ awareness of the potential safety issues regarding machine learning models. In addition, it includes up-to-date techniques for dealing with these issues, equipping readers with not only technical knowledge but also hands-on practical skills"-- Worldcat. Safety properties -- Machine learning basics -- Model evaluation methods -- Safety and security properties -- Practice -- Safety threats -- Decision tree -- K-nearest neighbor -- Linear regression -- Naive bayes -- Loss function and gradient descent -- Deep learning -- Safety solutions -- Verification of deep learning -- Enhancement to safety and security of deep learning -- Extended safety solutions -- Deep reinforced learning -- Testing techniques -- Reliability assessment -- Assurance of machine learning lifecycle -- Probabilistic graph models for feature robustness -- Appendix: mathematical foundations and competition -- probability theory -- Linear algebra -- Probabilistic graph models -- Competition: resilience to adversarial attack. Xiaowei Huang, Gaojie Jin, and Wenjie Ruan. Includes bibliographical references. Machine learning Data protection Artificial intelligence Machine learning Safety measures Computer security Q325.5 .H83 2023 006.31 H860m 9789811968136 CSPC 260708 20260708143535.0 eng