AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning
Industrial Problems Seminar
Pin-Yu Chen (IBM)
In this talk, I will share my research journey toward building an AI model inspector for evaluating, improving, and exploiting adversarial robustness for deep learning. I will start by providing an overview of research topics concerning adversarial robustness and machine learning, including attacks, defenses, verification, and novel applications. For each topic, I will summarize my key research findings, such as (i) practical optimization-based attacks and their applications to explainability and scientific discovery; (ii) Plug-and-play defenses for model repairing and patching; (iii) attack-agnostic robustness assessment; and (iv) data-efficient transfer learning via model reprogramming. Finally, I will conclude my talk with my vision of preparing deep learning for the real world and the research methodology of learning with an adversary.
This recording was created before the current policy requirements took effect, and therefore may not be accessible. To request this content in an accessible format, contact [email protected].