Feature Grinding: Efficient Backdoor Sanitation in Deep Neural Networks

no code implementations • 29 Sep 2021 • Nils Lukas, Charles Zhang, Florian Kerschbaum

Feature Grinding requires at most six percent of the model's training time on CIFAR-10 and at most two percent on ImageNet for sanitizing the surveyed backdoors.

Backdoor Attack

Indexing Context-Sensitive Reachability

1 code implementation • 3 Sep 2021 • Qingkai Shi, Yongchao Wang, Charles Zhang

Many context-sensitive data flow analyses can be formulated as a variant of the all-pairs Dyck-CFL reachability problem, which, in general, is of sub-cubic time complexity and quadratic space complexity.