Sumario: | It is our great pleasure to welcome you to the 2020 ACM 1st Workshop of Security and Privacy in Artificial Intelligence. This is the 1st SPAI workshop cohosted with ASIACCS conference, hosting a venue to collect presentation of research results or working-in-progress proposals in AI/ML security and privacy area. The workshop gathers submissions focusing on hot topics like adversarial machine learning, privacy-preserving machine learning, and generic attacks on neural networks. On the other side, we also welcome system design or application submissions to leverage AL/ML to solve conventional security topics, e.g., anomaly detection. The call for papers attracted submissions from Asia, Europe, and the United States. Due to pandemic impact, we gathered 13 submissions in total and accept 6 out of them. Each submission has been double-blindly reviewed by at least three reviewers. Comments and scores have been sent to authors for improving their work after completing the reviews. This workshop will have two keynote speakers. Nacolas Papernot from University of Toronto and Bo Li from University of Illinois at Urbana-Champaign. Nacolas will present this talk, "What does it mean for ML to be trustworthy?". He will explain what trustworthiness means to ML/AL and why it matters; Bo will talk about the goals, challenges, and interesting finding in Secure Learning In Adversarial Environments. We encourage attendees to attend the keynote and invited talk presentations. These valuable and insightful talks can and will guide us to a better understanding of the future of AL/ML security.
|