Security and Safety in AI: Adversarial Examples, Bias and Trust with Moustapha Cissé

In this episode I'm joined by Moustapha Ciss�, Research Scientist at Facebook AI Research Lab (or FAIR) Paris. Moustapha's broad research interests include the security and safety of AI systems, and we spend some time discussing his work on adversarial examples and systems that are robust to adversarial attacks. More broadly, we discuss the role of bias in datasets, and explore his vision for models that can identify these biases and adjust the way they train themselves in order to avoid taking on those biases.