Название: Security and Privacy in Federated Learning
Автор: Shui Yu, Lei Cui
Издательство: Springer
Год: 2023
Страниц: 142
Язык: английский
Формат: pdf (true), epub
Размер: 16.2 MB

In this book, the authors highlight the latest research findings on the security and privacy of Federated Learning systems. The main attacks and counterattacks in this booming field are presented to readers in connection with inference, poisoning, generative adversarial networks, differential privacy, secure multi-party computation, homomorphic encryption, and shuffle, respectively.

The book offers an essential overview for researchers who are new to the field, while also equipping them to explore this “uncharted territory.” For each topic, the authors first present the key concepts, followed by the most important issues and solutions, with appropriate references for further reading.

In the recent two decades, we have witnessed the dramatic development of Artificial Intelligence (AI in short), not only in Artificial Intelligence itself but also its applications in various sectors of human society. The appearance of deep learning pushed AI into another spring after a long winter. Nowadays, there are many successful stories of significant progress in various scientific fields with the help of AI, for example, the application of AI in biology, chemistry, law, and social science, to name a few.

However, Artificial Intelligence (AI) suffers a fundamental challenge, explainability: the conclusions obtained from Machine Learning based on big datasets are generally very useful, but we sometimes do not know why. People even treated AI as alchemy: the outputs of the same AI algorithm with the same inputs may vary from time to time, and AI practitioners sometimes even do not know what they will have before the deployment of AI.

Security and privacy protection in AI is far behind the fast development of AI and its applications. As we can see, AI is gradually permeating into our daily lives, and security and privacy are big challenges as AI needs sufficient information for their judgment and recommendation. As a result, we can see that AI and privacy protection are natural enemies. We can predict that majority (if not all) known attacks will be applied in AI applications, we need solutions. Particularly, digital privacy is an unprecedented challenge, and we face numerous new problems, for example, measurement of privacy, privacy modelling, privacy tools, and privacy pricing, to list a few.

In general, Federated Learning (FL) is a branch of Deep Learning, which is a powerful tool to address various complex problems in the past decades. Google proposed Federated Learning as a variation of Deep Learning in order to address the privacy concern from data owners. Federated Learning (FL) is a big step for privacy protection in Machine Learning; however, it is not perfect. The Federated Learning framework allows learning participants to keep their data locally and download the training model from a central server or servers to execute a local training. The updates will be uploaded to the server(s) for a further aggregation for the next round of training until an acceptable global model is reached. Despite the advancement of its computing model, Federated Learning still faces many security and privacy challenges, which have attracted a lot of attention from academia and industry.

We classify the security and privacy research in Federated Learning into two categories: problem based and tool based. In our understanding, problem-oriented research focuses on problems and proposes solutions. At the same time, tools-oriented research usually depends on tools to address problems.

In order to serve our readers in a flexible way, we organize the book into three parts: problem oriented, tool oriented, and the promising future directions: Chaps. 2, 3, and 4 are problem oriented, where we present the hot problems and their related solutions in Federated Learning. In Chaps. 5–8, we shift to present the solutions using the available tools, differential privacy, and cryptography. We have to note that we only introduce the concept and very basics of the tools (especially for cryptography) for readers to understand the related security and privacy research in the federated learning field. If readers expect to continue the research using these tools, we suggest them to read the classic textbooks of the tools following the related references, respectively. In Chap. 9, we boldly present some of our understanding on the security and privacy landscape in the near future for the possible reference of our readers. We know it is hard to predict the future, but we cannot help ourselves to share our thinking with readers, hoping it would be helpful for them. Each chapter or part of the book is relatively independent, and readers can choose any order to use the book according to their needs.

Federated Learning is a new field, security and privacy in Federated Learning is a newer subfield. Our purpose is to introduce interested readers to this promising research area. The book could be used as an introductory subject for senior undergraduate students, it can also be used for postgraduate students or researchers as a reference for their research work. We hope this book brings our readers an overview of the field, and paves a starting ground for them to further explore the uncharted land of the domain in both theoretical and application perspectives.

The book is self-contained, and all chapters can be read independently. It offers a valuable resource for master’s students, upper undergraduates, Ph.D. students, and practicing engineers alike.