Trustworthy Machine Learning

The widely deployed machine learning models and algorithms in the inter-connected intelligent systems, such as IoT systems, have demonstrated a high level of potential for human daily life. Emerging as a novel technique to support the intelligent systems for a wide range of societal activities, such as autonomous unmanned aerial vehicles network, transportation systems and health care applications, trustworthy machine learning (TML) has become a focus for worldwide researchers. TML is designed as a pivotal and technical solution to ensure the various learning algorithms behave in a socially responsible manner and meet certain compliance requirements from the government and international organisations. One main goal is to investigate the different principles and constraints for TML-SPPIoT to be applied in IoT systems for a security and privacy preserving goal by a broad spectrum of researchers and practitioners. This workshop will focus on discussing the theories, principles, and experiences of developing trustworthy machine learning algorithms and models for such intelligent IoT systems, considering the mass inter-connected devices such as UAV, edge sensors and so on. This workshop will be the first attempt of gathering researchers interested in the emerging and interdisciplinary filed of trustworthy machine learning from its technical perspective and bringing the impacts in intelligent IoT systems for a goal of security and privacy. This workshop will highlight the recent related works and foster unprecedented chance to bridge the research gaps across the topics of deep learning, machine learning, IoT, security, fairness, privacy and so on. This workshop will conduct a reflection on foundations (theory and application) of trustworthy machine learning and lay out a positive vision for future collaboration and research activities for intelligent IoT systems.