Haojin Zhu

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.

This book presents the security and privacy challenges of the smart home following the logic of “terminal device – voice interface – application platform”. For each component, the authors provide answers to the three questions: 1) In the terminal device layer, how to conduct cross-layer privacy breach analysis and provide effective countermeasures; 2) In the voice interface layer, how to design effective and lightweight schemes to defend against voice spoofing; 3) In the application layer, how to design an effective anomaly detection system without breaching the application platform. The authors conduct a thorough analysis of the security threats and challenges in each component of the smart home, review the existing state-of-the-art solutions proposed by other researchers, and elaborate on proposed countermeasures. This book aims to provide both security threats analysis and state-of-the-art countermeasures for the smart home network.

This book presents the security and privacy challenges of the smart home following the logic of “terminal device – voice interface – application platform”. For each component, the authors provide answers to the three questions: 1) In the terminal device layer, how to conduct cross-layer privacy breach analysis and provide effective countermeasures; 2) In the voice interface layer, how to design effective and lightweight schemes to defend against voice spoofing; 3) In the application layer, how to design an effective anomaly detection system without breaching the application platform. The authors conduct a thorough analysis of the security threats and challenges in each component of the smart home, review the existing state-of-the-art solutions proposed by other researchers, and elaborate on proposed countermeasures. This book aims to provide both security threats analysis and state-of-the-art countermeasures for the smart home network.

This book presents several novel approaches to model the interaction between the attacker and the defender and assess the security of Vehicular Ad Hoc Networks (VANETs). The first security assessment approach is based on the attack tree security assessment model, which leverages tree based methods to analyze the risk of the system and identify the possible attacking strategies the adversaries may launch. To further capture the interaction between the attacker and the defender, the authors propose to utilize the attack-defense tree model to express the potential countermeasures which could mitigate the system. By considering rational participants that aim to maximize their payoff function, the brief describes a game-theoretic analysis approach to investigate the possible strategies that the security administrator and the attacker could adopt. A phased attack-defense game allows the reader to model the interactions between the attacker and defender for VANET security assessment. The brief offers a variety of methods for assessing the security of wireless networks. Professionals and researchers working on the defense of VANETs will find this material valuable.