Differential halo zonotopes enable static verification of global robustness in DNNs by jointly propagating pairs of perturbed inputs while bounding divergence, with a relaxed confidence-based variant.
In: 2018 IEEE Symposium on Security and Privacy (SP)
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 7roles
dataset 1polarities
use dataset 1representative citing papers
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.
A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
Code language models show no transferable security understanding from code diffs alone, rely on commit messages, miss over 93% of fixes at 0.5% false positive rate, and suffer large drops under group or temporal splits.
No finite formal verifier can certify all policy-compliant AI instances of arbitrarily high Kolmogorov complexity.
A literature review that defines silent physical-action failures in Physical AI and identifies the lack of complete runtime authorization boundaries across surveyed technical streams.
Physical admissibility is defined as a prediction-control interface using kinematic, dynamic, and composed-horizon conditions to reject invalid dynamics proposals, with AUC 0.957 on LeRobot PushT and 87-89% prevention of invalid actions in interventions.
citing papers explorer
-
Differential Zonotopes for Verifying Global Robustness of DNNs
Differential halo zonotopes enable static verification of global robustness in DNNs by jointly propagating pairs of perturbed inputs while bounding divergence, with a relaxed confidence-based variant.
-
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.
-
Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement
A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
-
Incompleteness of AI Safety Verification via Kolmogorov Complexity
No finite formal verifier can certify all policy-compliant AI instances of arbitrarily high Kolmogorov complexity.
-
Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems
A literature review that defines silent physical-action failures in Physical AI and identifies the lack of complete runtime authorization boundaries across surveyed technical streams.
-
Can Predicted Dynamics Exist in the Physical World?
Physical admissibility is defined as a prediction-control interface using kinematic, dynamic, and composed-horizon conditions to reject invalid dynamics proposals, with AUC 0.957 on LeRobot PushT and 87-89% prevention of invalid actions in interventions.