AI-Sec 2021 : Cyber Security and Adversarial Machine Learning: Emerging Attacks and Mitigation Strategies



Machine Learning is making our daily lives as digital as possible, and this new era is called Artificial Intelligence. The binding force behind the rapid growth of machine learning (or deep learning) is enterprises’ technological advances. In recent years, machine learning algorithms have been applied widely in various fields, such as healthcare, transportation, energy, autonomous car, and many more. With the rapid developments of deep learning applications, it is crucial to understand the security concern into account when implementing the models. While deep learning applications allow notable benefits for enterprise applicaions, AI models’ security is disregarded by the developer community so far. However, security is also an essential part of the AI models because attackers can manipulate the AI model itself.


In this context, this book will address the cybersecurity and security of the AI application challenges connected with the enterprises, which will provide a bigger picture of the theories, intelligent methods, methods, and open research directions in this domain. Furthermore, the proposed book will assist as a single source of reference for acquiring knowledge on the technology, process involved in the next-generation cybersecurity.

Target Audience

This book intends to bring collectively the analyses and insights of researchers and scientists worldwide, but practitioners are also more than welcomed as chapter authors. All types of contributions are considered, ranging from real-life case studies to best practices, conceptual papers, empirical studies, literature reviews, and the like. This book aims to analyze AI and cybersecurity from a holistic perspective and provide a balanced and critical account of the sector’s digitalization, opportunities, impact and challenges and showcase a wide variety of opinions and viewpoints.

  • Foundations of understanding adversarial machine learning
  • Theory and algorithms for attacking with adversarial learning
  • Theory and algorithms of defending adversarial attacks
  • Novel applications of adversarial learning and security
  • Business data security with adversarial training
  • Medical/health informatics with security
  • Biological data analysis with security
  • Biometric recognition with security and privacy
  • Explainable machine learning for cyberspace security and safety
  • Human-machine intelligence for cyberspace security and safety
  • Cloud security and AI
  • Secure AI modelling and architecture
  • Novel cryptographic mechanism for AI
  • Cyberspace security and safety for 5G/6G
  • Cyberspace security and safety for industry 4.0/5.0

Submission Procedure

Researchers and practitioners are invited to submit on or before May 12, 2021, a chapter proposal of 1,000 to 2,000 words clearly explaining the mission and concerns of his or her proposed chapter. Authors will be notified by May 26, 2021 about the status of their proposals and sent chapter guidelines.Full chapters are expected to be submitted by July 25, 2021, and all interested authors must consult the guidelines for manuscript submissions at prior to submission. All submitted chapters will be reviewed on a double-blind review basis. Contributors may also be requested to serve as reviewers for this project.

Note: There are no submission or acceptance fees for manuscripts submitted to this book publication, Cyber Security and Adversarial Machine Learning: Emerging Attacks and Mitigation Strategies. All manuscripts are accepted based on a double-blind peer review editorial process.

Important Dates

May 12, 2021: Proposal Submission Deadline
May 26, 2021: Notification of Acceptance
July 25, 2021: Full Chapter Submission
September 7, 2021: Review Results Returned
October 19, 2021: Final Acceptance Notification
November 2, 2021: Final Chapter Submission


Ferhat Ozgur Catak
Simula Research Lab. -