PAC-guaranteed framework for counting inputs satisfying logical properties in neural networks, instantiated as NPAQ for binarized networks and applied to robustness, trojan efficacy, and bias analyses.
Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Quantitative Verification of Neural Networks And its Security Applications
PAC-guaranteed framework for counting inputs satisfying logical properties in neural networks, instantiated as NPAQ for binarized networks and applied to robustness, trojan efficacy, and bias analyses.