A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
Limits of AI Safety Verification 17 E
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 3roles
dataset 1polarities
use dataset 1representative citing papers
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.
citing papers explorer
-
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.
-
Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study
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.
-
Incompleteness of AI Safety Verification via Kolmogorov Complexity
No finite formal verifier can certify all policy-compliant AI instances of arbitrarily high Kolmogorov complexity.