Guest
Recently, we’ve seen an explosion of AI datasets and models that are impacting millions around the world each day in ways big and small. During development of an AI model, conditions are carefully controlled to obtain the best possible performance — but in the real world, where models are ultimately deployed, conditions are rarely perfect, and risks are abundant. Our research on adversarial robustness aims to seek out soft spots in popular machine learning techniques to defend against them by simulating — and mitigating — new attacks to ultimately design more robust models and algorithms. Learn more about the field of secure AI research here [] and explore the open source adversarial robustness toolkit below:
