Explore a comprehensive 15-minute IEEE conference talk on certified robustness for deep neural networks. Delve into the research presented by Linyi Li and Bo Li from the University of Illinois Urbana-Champaign, USA, and Tao Xie from the Key Laboratory of High Confidence Software Technologies at Peking University, China. Gain insights into the latest advancements and methodologies for ensuring the reliability and resilience of deep learning models against adversarial attacks and perturbations.
Overview
Syllabus
SoK: Certified Robustness for Deep Neural Networks
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
RAB - Provable Robustness Against Backdoor Attacks
-
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
-
Model Orthogonalization - Class Distance Hardening in Neural Networks for Better Security
-
Towards Evaluating the Robustness of Neural Networks
-
Safety and Robustness for Deep Learning with Provable Guarantees - Marta Kwiatkowska - Oxford
-
Getting Robust - Securing Neural Networks Against Adversarial Attacks
