05150nam a22005895i 4500 978-3-031-57389-7 DE-He213 20251030112240.0 cr nn 008mamaa 240529s2024 sz | s |||| 0|eng d 9783031573897 978-3-031-57389-7 10.1007/978-3-031-57389-7 doi TK5105.5-5105.9 UKN bicssc COM043000 bisacsh UKN thema Li, Shaofeng. author. aut http://id.loc.gov/vocabulary/relators/aut 77712 Backdoor Attacks against Learning-Based Algorithms [electronic resource] / by Shaofeng Li, Haojin Zhu, Wen Wu, Xuemin (Sherman) Shen. 1st ed. 2024. Cham : Springer Nature Switzerland : Imprint: Springer, 2024. XI, 153 p. 58 illus., 56 illus. in color. online resource. text txt rdacontent computer c rdamedia online resource cr rdacarrier text file PDF rda Wireless Networks, 2366-1445 Introduction -- Literature Review of Backdoor Attacks -- Invisible Backdoor Attacks in Image Classification Based Network Services -- Hidden Backdoor Attacks in NLP Based Network Services -- Backdoor Attacks and Defense in FL -- Summary and Future Directions. 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 enormous threat that backdoor attacks pose to model supply chain security, they have received widespread attention from academia and industry. This book focuses on exploiting backdoor attacks in the three types of DNN applications, which are image classification, natural language processing, and federated learning. Based on the observation that DNN models are vulnerable to small perturbations, this book demonstrates that steganography and regularization can be adopted to enhance the invisibility of backdoor triggers. Based on image similarity measurement, this book presents two metrics to quantitatively measure the invisibility of backdoor triggers. The invisible trigger design scheme introduced in this book achieves a balance between the invisibility and the effectiveness of backdoor attacks. In the natural language processing domain, it is difficult to design and insert a general backdoor in a manner imperceptible to humans. Any corruption to the textual data (e.g., misspelled words or randomly inserted trigger words/sentences) must retain context-awareness and readability to human inspectors. This book introduces two novel hidden backdoor attacks, targeting three major natural language processing tasks, including toxic comment detection, neural machine translation, and question answering, depending on whether the targeted NLP platform accepts raw Unicode characters. The emerged distributed training framework, i.e., federated learning, has advantages in preserving users' privacy. It has been widely used in electronic medical applications, however, it also faced threats derived from backdoor attacks. This book presents a novel backdoor detection framework in FL-based e-Health systems. We hope this book can provide insightful lights on understanding the backdoor attacks in different types of learning-based algorithms, including computer vision, natural language processing, and federated learning. The systematic principle in this book also offers valuable guidance on the defense of backdoor attacks against future learning-based algorithms. Computer networks . 60157 Wireless communication systems. 65781 Mobile communication systems. 65782 Machine learning. 55059 Computer Communication Networks. 65689 Wireless and Mobile Communication. 65786 Machine Learning. 55059 Zhu, Haojin. author. aut http://id.loc.gov/vocabulary/relators/aut 77713 Wu, Wen. author. aut http://id.loc.gov/vocabulary/relators/aut 76575 Shen, Xuemin (Sherman). author. aut http://id.loc.gov/vocabulary/relators/aut 70857 SpringerLink (Online service) Springer Nature eBook Printed edition: 9783031573880 Printed edition: 9783031573903 Printed edition: 9783031573910 Wireless Networks, 2366-1445 67497 https://doi.org/10.1007/978-3-031-57389-7 ZDB-2-SCS ZDB-2-SXCS 60245 60245