Call for Papers
In recent years, adversarial learning methods are shown to be a key technique that leads to exciting breakthroughs and new challenges of many machine learning and data mining tasks. Examples include improved training of generative models (e.g., generative adversarial nets), adversarial robustness of machine learning systems in different domains (e.g., adversarial attacks, defenses, and property verification), and robust representation learning (e.g., adversarial loss for learning embedding), to name a few. Generally speaking, the idea of “learning with an adversary” is crucial for expanding the learning capability, ensuring trustworthy decision making, and enhancing generalizability of machine learning and data mining methods.
This workshop also aims to bridge theory and practice by encouraging theoretical studies motivated by adversarial ML/DM problems, such as robust (minimax) optimization and game theory. The program of this workshop will include: (i) invited talks covering different aspects and recent advances of adversarial learning methods, and (ii) open call track for paper submissions. Submitted papers will be peer-reviewed by the technical program committee. Accepted papers will be presented in a recorded format with live Q&A sessions. Each accepted paper will be made available on a public website and will not be considered as a publication. Short version of a full paper under review by other conferences or journals can be submitted to our workshop, but the authors should check the dual submission policy of the respective venue.
Topics of interest include but are not limited to:
Adversarial attacks and defenses in machine learning and data mining
Provably robust machine learning methods and systems
Robustness certification and property verification techniques
Representation learning, knowledge discovery and model generalizability
Generative models and their applications (e.g., generative adversarial nets)
Robust optimization methods and (computational) game theory
Explainable and fair machine learning models via adversarial learning techniques
Transfer learning, multi-agent adaptation, self-paced learning
Privacy and security in machine learning systems
Novel applications and innovations using adversarial machine learning and data mining