Formal verification of neuro-symbolic cyber-physical systems, such as drones, medical devices and robots, is complicated. Neural components must be trained to be optimal with respect to the available data as well as the safety specifications, and then verified using specialised solvers. Symbolic models of the "cyber" and "physical" behaviour of the system must be constructed and verified in interactive theorem provers (ITPs), often requiring mature mathematical libraries to reason about the interplay of discrete and continuous dynamics, preferably obtaining infinite time-horizon guarantees. Finally, the results of the two already challenging verification tasks need to be integrated into a single proof in a coherent and consistent way, whilst preserving deployability of the resulting model. In this paper we present a compositional methodology for constructing such proofs. The Vehicle framework provides a functional, domain-specific language for specifying, training, and verifying neural components. We extend Vehicle to allow integration with any ITP with minimal effort, thereby bridging the gap between the neural and symbolic proofs. First, we describe how Vehicle’s standard bidirectional type checker can be reused to transpile neural specifications into an intermediate representation targeting multiple theorem provers. Second, we integrate Vehicle with Rocq, Isabelle/HOL, Agda and the industrial prover Imandra; and showcase a generic infinite time-horizon safety proof of a discrete cyber-physical system with a neural network controller in each ITP. Finally, to put the idea of compositional neural-cyber-physical system verification to the test, we use the Mathematical Components libraries in Rocq to verify infinite time-horizon safety of a medical device, modelled as a continuous cyber-physical system with a neural controller. To our knowledge, this is the first result of this kind in a general purpose ITP; and a result that was only feasible thanks to the compositionality provided by Vehicle's functional interface.

Recent advances in the verification of deep neural networks (DNNs) have opened the way for a broader usage of DNN verification technology in many application areas, including safety-critical ones. However, DNN verifiers are themselves complex programs that have been shown to be susceptible to errors and numerical imprecision; this, in turn, has raised the question of trust in DNN verifiers. One prominent attempt to address this issue is enhancing DNN verifiers with the capability of producing certificates of their results that are subject to independent algorithmic checking. While formulations of Marabou certificate checking already exist on top of the state-of-the-art DNN verifier Marabou, they are implemented in C++, and that code itself raises the question of trust (e.g., in the precision of floating point calculations or guarantees for implementation soundness). Here, we present an alternative implementation of the Marabou certificate checking in Imandra - an industrial functional programming language and an interactive theorem prover (ITP) - that allows us to obtain full proof of certificate correctness. The significance of the result is two-fold. Firstly, it gives stronger independent guarantees for Marabou proofs. Secondly, it opens the way for the wider adoption of DNN verifiers in interactive theorem proving in the same way as many ITPs already incorporate SMT solvers.

Neural networks are increasingly relied upon as components of complex safety-critical systems such as autonomous vehicles. There is high demand for tools and methods that embed neural network verification in a larger verification cycle. However, neural network verification is difficult due to a wide range of verification properties of interest, each typically only amenable to verification in specialised solvers. In this paper, we show how Imandra, a functional programming language and a theorem prover originally designed for verification, validation and simulation of financial infrastructure can offer a holistic infrastructure for neural network verification. We develop a novel library CheckINN that formalises neural networks in Imandra, and covers different important facets of neural network verification.

We present a proof procedure for univariate real polynomial problems in Isabelle/HOL. The core mathematics of our procedure is based on univariate cylindrical algebraic decomposition. We follow the approach of untrusted certificates, separating solving from verifying: efficient external tools perform expensive real algebraic computations, producing evidence that is formally checked within Isabelle’s logic. This allows us to exploit highly-tuned computer algebra systems like Mathematica to guide our procedure without impacting the correctness of its results. We present experiments demonstrating the efficacy of this approach, in many cases yielding orders of magnitude improvements over previous methods.