Proposes spectral norm of Fisher Information Matrix as attack-agnostic robustness metric with closed-form bounds for common architectures and correlation to adversarial vulnerability.
arXiv preprint arXiv:2312.04960 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Identifies sensitivity as the source of both discriminability and vulnerability in FC classifiers versus robustness in l2 classifiers, and introduces HPM prototype fusion plus MSA evaluation to improve adversarial robustness.
citing papers explorer
-
Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
Proposes spectral norm of Fisher Information Matrix as attack-agnostic robustness metric with closed-form bounds for common architectures and correlation to adversarial vulnerability.