STBP computes exact closed-form bounds for the first convolutional layer of spatio-temporal networks and propagates scalable approximations through the rest to certify robustness under subset-frame or patch perturbations.
Alhussein Fawzi, Hamza Fawzi, and Pascal Frossard
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
TASER is a Stein-operator regularization method that improves adversarial robustness on CIFAR-10 benchmarks while preserving clean accuracy.
citing papers explorer
-
Hybrid Robustness Verification for Spatio-Temporal Neural Networks
STBP computes exact closed-form bounds for the first convolutional layer of spatio-temporal networks and propagates scalable approximations through the rest to certify robustness under subset-frame or patch perturbations.
-
TASER: Task-Aware Stein Regularisation for Geometry-Driven Robustness
TASER is a Stein-operator regularization method that improves adversarial robustness on CIFAR-10 benchmarks while preserving clean accuracy.