Robustness, Verification, Privacy: Addressing Machine Learning Adversaries
2020-12-08T17:00:00-08:00 - 2020-12-08T19:00:00-08:00
- Moderator: Avrim Blum
- On-demand video (45 minutes)
- Live Q&A (10 min)
- Break (5 min)
- Ask Me Anything Chat (up to an hour)
Abstract: We will present cryptography inspired models and results to address three challenges that emerge when worst-case adversaries enter the machine learning landscape. These challenges include verification of machine learning models given limited access to good data, training at scale on private training data, and robustness against adversarial examples controlled by worst case adversaries.