Recently, research in adversarial machine learning has brought to light important potential security issues with systems that people use on a daily basis for search and discovery. While adversarial examples are well understood in computer vision tasks, the harmful effects of the malicious application of machine learning are less well-understood in information retrieval and recommendation systems. The issues include: injection of adversarial-crafted fake users, adversarial perturbation of multimedia data in training sets or background collections, and adversarial structural noise on graph structure in order to improve search and recommendation in real-world environments, research is necessary that will allow us to discover, understand, and control the adverse impact of adversarial machine learning. In this workshop, we aim to bring together researchers from the fields of adversarial machine learning, information retrieval, and recommender systems to discuss recent advances and research directions that could be further exploited to broaden the frontier in the field. The purpose of the 1st International Workshop on Adversarial Machine Learning for Recommendation and Search (AdveRSe) is to provide a meeting forum for stimulating and disseminating research in Adversarial Machine Learning for Recommendation and Search Systems, where researchers can network and discuss their research results in an informal way. The Half-Day Workshop will take place online on November 1-5, 2021 in conjunction with the 30th ACM International Conference on Information and Knowledge Management (CIKM 2021), hosted in Gold Coast, Queensland, Australia.Overview
List of Organizers