Quantum Robustness
in
Artificial Intelligence
Tentative Timeline:
Title, Abstract, Author List submission:
March 30, 2025
Full Book Chapter Draft Due:
May 30, 2025
Review reports and revised chapter due:
August 30, 2025
Publication of Final Book:
November 2025
Book Title: Quantum Robustness in Artificial Intelligence
Publisher: Springer Quantum Science and Technology Series
Book Editor: Professor Muhammad Usman
Submissions are now open via email at muhammad.usman@csiro.au
Guidelines for manuscript preparation are Here
Tentative List of topics: This book will be a collection of book chapters from world leading quantum and classical AI/ML experts. The book is divided in five sections, with a tentative list of topics is as follows:
SECTION I: Classical ML/AI and Adversarial Aspects
Fundamentals of classical AI/ML
Fundamentals of classical adversarial AI/ML
SECTION II: Quantum ML/AI
Fundamentals of quantum AI/ML
Novel quantum AI/ML architectures and benchmarks
Efficient data encoding for quantum AI/ML
Quantum robustness in AI/ML (not linked to adversarial aspects)
SECTION III: Quantum Adversarial ML/AI
Fundamentals of quantum adversarial AI/ML
Transferability of adversarial attacks between classical and quantum AI/ML
Transferability of adversarial attacks between quantum AI/ML models
Analytical theory of quantum adversarial robustness
Quantum Generative Adversarial Networks
SECTION IV: Implementation Aspects of Quantum ML/AI
Role of noise or errors on quantum adversarial robustness
Experimental implementation of quantum adversarial robustness and related challenges
Quantum adversarial robustness with quantum error correction
Applications of quantum adversarial AI/ML
Quantum adversarial AI: Future directions and road-map for applications
SECTION V: Selected Topics on Quantum Robustness Beyond AI/ML
Summary:
Machine learning (ML) and artificial intelligence (AI) algorithms are nowadays ubiquitous for image analysis and signal processing tasks. Likewise, the autonomous and robotic systems deployed in military and Defence applications, such as security, surveillance and targeting systems, are or will be based on ML/AI algorithms. Despite their high efficiency and accuracy, ML and AI algorithms can be fooled by an adversary through manipulation or spoofing of data (also known as adversarial attacks), which poses serious threat for security sensitive applications.
The integration of quantum computing in ML and AI is rapidly progressing, which offers an opportunity to create new quantum ML/AI models which are designed to fundamentally exploit quantum mechanical properties for gaining advantages such as in training speed or feature extraction accuracy. This has raised an important question that whether quantum AI/ML algorithms are also as vulnerable as classical AI/ML models, giving birth to a new field of research known as quantum adversarial AI/ML. This book will provide a comprehensive overview of the research in the emerging field of quantum adversarial AI/ML and include seminal work from world-leading quantum and classical AI/ML experts. The book aims to cover an up-to-date summary of the cutting-edge recent work on advancing quantum AI/ML and its benchmarking against adversarial attacks. This will be the first such book on the topic and will provide an excellent reference for graduate students and industry experts who are interested in quantum AI/ML for security sensitive autonomous systems. The book will also cover quantum robustness beyond AI/ML to provide a comprehensive understanding of the field of research.