The Theme 

Machine learning plays an increasingly important role in the field of artificial intelligence, such as image classification, computer vision, natural language processing, recommendation systems, etc.. Meanwhile, in the era of big data, both system security and data privacy are particularly important. Machine learning vulnerabilities and privacy preservation learning have attracted growing interest in the fields of artificial intelligence, information security, and data privacy. The aims of this special issue are: (1) to present the cutting-edge research about security and privacy in machine learning; (2) to provide a platform for researchers and practitioners to present their views on future research trends in building secure and privacy-preserving learning systems. Topics of interest include but are not limited to:

• Poisoning attack and defense

• Evasion attacks and defense

• Generation techniques of adversarial examples

• Detection techniques of adversarial examples

• Mitigation and defense techniques of adversarial examples

• Interpretability of deep neural networks for secure machine learning

• Interpretability of machine learning models for secure machine learning Adversarial examples in real-world applications

• Adversarial machine learning

• Federated learning

• Privacy-preserving machine learning techniques

• Privacy-preserving learning in real-world applications

• Immune computation in secure learning

• Evolutionary computation in secure machine learning

Manuscript Preparation and Submission

Submitted manuscripts must not have been previously published or currently submitted for conference/journal publication elsewhere. The manuscripts should be prepared according to the ``Information for Authors" section of the journal found at: https://cis.ieee.org/publications/ieee-transactions-on-artificial-intelligence/information-for-authors-tai and submission should be done through the journal submission website: https://mc.manuscriptcentral.com/ tai-ieee. Follow the submission instructions given on this site; please select the article type as “SI: S&P in Machine Learning”.  

Guest Editors

• Wenjian Luo, School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China, Email: luowenjian@hit.edu.cn

• Yaochu Jin, Department of Computer Science, Univeristy of Surrey, UK, Email: yaochu.jin@surrey.ac.uk

• Catherine Huang, McAfee LLC, US, Email: Catherine_Huang@McAfee.com