Machine learning techniques have been applied to a wide range of real life applications. However, the study on security issues is lagging behind. Despite of the remarkable success in the application of machine learning techniques, many recent studies reveal their vulnerabilities in an adversarial environment, in which an adversary misleads the decision of the system on purpose by manipulating data. As traditional machine learning methods do not consider the influence of an adversarial attack, their performance may drop significantly.

This workshop aims to bring together researchers in the fields of machine learning, computer security, and security-related applications, working to investigate vulnerability issues and improve robustness of machine learning in an adversarial environment. The objectives include but not limit to:

• Provide an overview of state-of-the-art adversarial learning;
• Provide theoretical and empirical explanation on adversary-aware machine learning methods;
• Explore new, potential adversarial attack; and
• Present and report new applications of adversarial learning.

The program may include plenary and invited talks, panel discussion and poster presentation. An expected outcome of this workshop is the formation of research collaboration effort, and a special issue of the International Journal on Machine Learning and Cybernetics focusing on this topic.
We welcome submissions on all facets of machine learning in an adversarial environment. Topics include, but not limited to the following:

• Statistical Machine Learning
• Intelligent and Fuzzy Control
• Pattern Recognition
• Ensemble Method
• Evolutionary Computation
• Fuzzy and Rough Set
• Data and Web Mining
• Information Retrieval
• Bioinformatics
• Biometrics
• Adversarial Learning
• Web Intelligence and Technology
• Semantics and Ontology Engineering
• Intelligent Business Computing
• Cybersecurity
• Multicriteria Decision Making
• Soft Computing
• Intelligent Systems
• Speech, Image and Video Processing
• Decision Support Systems
• Social Networks and Ubiquitous Intelligence
• Generative Adversarial Network

The manuscripts should be between 4 to 6 pages in length. Any manuscript of more than 6 pages will be charged for pages exceeding the limit. An electronic copy (in word or pdf) of a complete manuscript can be submitted to “Workshop on Adversarial Machine Learning” in the submission system.

• Fabio Roli, University of Cagliari, Italy
• Daniel Yeung, Past President, SMCS, IEEE
• Patrick Chan, South China University of Technology, China
• Battista Baggio, University of Cagliari, Italy

• Submission Due: 20th May 2024
• Notification of Acceptance: 20th July 2024
• Registration Due: 20th August 2024

Please contact Dr. Patrick Chan