Neural Network Verification for the Masses (of AI graduates)
This work tackles the problem of integrating verification into AI education for students and educators, but it is incremental as it focuses on reporting experiences rather than introducing new methods.
The paper addresses the shortage of accessible tools and teaching materials for incorporating verification into AI programs, particularly for neural network safety against adversarial attacks, by reporting on the experiences and challenges faced by the LAIV lab in engaging AI and Robotics MSc students in verification projects.
Rapid development of AI applications has stimulated demand for, and has given rise to, the rapidly growing number and diversity of AI MSc degrees. AI and Robotics research communities, industries and students are becoming increasingly aware of the problems caused by unsafe or insecure AI applications. Among them, perhaps the most famous example is vulnerability of deep neural networks to ``adversarial attacks''. Owing to wide-spread use of neural networks in all areas of AI, this problem is seen as particularly acute and pervasive. Despite of the growing number of research papers about safety and security vulnerabilities of AI applications, there is a noticeable shortage of accessible tools, methods and teaching materials for incorporating verification into AI programs. LAIV -- the Lab for AI and Verification -- is a newly opened research lab at Heriot-Watt university that engages AI and Robotics MSc students in verification projects, as part of their MSc dissertation work. In this paper, we will report on successes and unexpected difficulties LAIV faces, many of which arise from limitations of existing programming languages used for verification. We will discuss future directions for incorporating verification into AI degrees.