Trustable, Verifiable and Auditable Artificial Intelligence

School Overview

Artificial intelligence, particularly machine learning, has advanced significantly and demonstrated tremendous achievements in various domains (e.g., computer vision, NLP, robotics, etc.) to solve non-trivial problems. Federated learning (FL) is one promising machine learning approach that trains a collective machine learning model using sharing data owned by various parties. It leverages many emerging privacy-preserving to protect data owner privacy in FL. However, FL still faces multiple challenges that may limit its applications in real-world use scenarios. For example, FL is still at the risk of various kinds of attacks that may result in leakage of individual data source privacy or degraded joint model accuracy. In other words, many existing FL solutions are still exposed to various security and privacy threats. Developing verifiable, reliable, robust, auditable, explainable, and unbiased FL can solve these challenges. This school aims to bring together FL researchers and practitioners to address the additional security and privacy threats and challenges in FL to make its mass adoption and widespread acceptance in the community. The target audience for the school is university students, postdocs, researchers, and professionals in machine learning. However, the school welcomes anyone with the necessary background. The school is open to participants from all over the world; all talks will be in English.

Important Dates

All dates are 11:59PM Singapore Time
Registration due: November 18, 2022
School day: December 12-14, 2022

Organizers

School Lecturers