Machine Learning in Montpellier, Theory & Practice
In this talk, we will focus on an important security concern in modern day machine learning, namely adversarial example attacks. The vulnerability of state-of-the-art models to these attacks has genuine security implications especially when models are used in AI-driven technologies, e.g., for self-driving cars or fraud detection. Besides security issues, these attacks show how little we know about the models used every day in the industry, and how little control we have over them. The problem of adversarial example attacks is still open and constitutes an active area of research. We will provide some insights allowing to navigate through this research field essentially presenting the current state-of-knowledge on how these attacks work, and how to mitigate them by using some notions of learning theory and optimization.