Vehicle enables compositional verification of neural controllers in discrete and continuous cyber-physical systems across Rocq, Isabelle/HOL, Agda, and Imandra, including the first infinite time-horizon safety proof for a continuous medical device in a general-purpose ITP.
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
4 Pith papers cite this work, alongside 900 external citations. Polarity classification is still indexing.
4
Pith papers citing it
900
external citations · Crossref
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
BDDs deliver an exact, canonical, memory-efficient representation of ACAS-Xu LUTs that supports direct formal verification and embedded deployment.
citing papers explorer
-
Compositional Neural-Cyber-Physical System Verification in the Interactive Theorem Prover of Your Choice
Vehicle enables compositional verification of neural controllers in discrete and continuous cyber-physical systems across Rocq, Isabelle/HOL, Agda, and Imandra, including the first infinite time-horizon safety proof for a continuous medical device in a general-purpose ITP.
-
Quantitative Linear Logic for Neuro-Symbolic Learning and Verification
QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
-
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.
-
Compressing ACAS-Xu Lookup Tables with Binary Decision Diagrams
BDDs deliver an exact, canonical, memory-efficient representation of ACAS-Xu LUTs that supports direct formal verification and embedded deployment.