arXiv subjects

Mike Dodds

Publications and source records attributed to Mike Dodds.

8 recordsLinked to original sources

arXiv2026

FVSpec: Real-World Property-Based Tests as Lean Challenges

As AI systems generate an ever-growing share of the world's code, formal verification offers a principled way to ensure that code is correct, and AI itself may be able to shoulder much of the verification burden. Yet we lack a clear picture of how well today's models and agents perform on verification tasks drawn from real-world software, since existing benchmarks rely largely on curated or synthetic problems, or focus on math rather than program verification. To close this gap, we present a benchmark for evaluating AI on real-world formal software verification tasks. We first scrape 7,413 distinct property-based tests (PBTs) from real-world Python repositories, then automatically translate 2,623 of them (35%) into 9,415 Lean 4 specifications with sorry placeholders (3.5 formalizations/PBT). Translating PBTs to Lean specs is challenging: it requires modeling Python in Lean, inferring the property encoded in a PBT, and handling side effects. We describe an agentic pipeline for transpiling PBTs into Lean, evaluate coverage and quality metrics, and provide baselines for proof generation using several approaches. All code (scraper and agents) and data (PBTs and Lean specs) are open source.

cs.SE↗

arXiv2026

Trustworthy Runtime Verification via Bisimulation (Extended Experience Report)

When runtime verification is used to monitor safety-critical systems, it is essential that monitoring code behaves correctly. The Copilot runtime verification framework pursues this goal by automatically generating C monitor programs from a high-level DSL embedded in Haskell. In safety-critical domains, every piece of deployed code must be accompanied by an assurance argument that is convincing to human auditors. However, it is difficult for auditors to determine with confidence that a compiled monitor cannot crash and implements the behavior required by the Copilot semantics. In this paper we describe CopilotVerifier, which runs alongside the Copilot compiler, generating a proof of correctness for the compiled output. The proof establishes that a given Copilot monitor and its compiled form produce equivalent outputs on equivalent inputs, and that they either crash in identical circumstances or cannot crash. The proof takes the form of a bisimulation broken down into a set of verification conditions. We leverage two pieces of SMT-backed technology: the Crucible symbolic execution library for LLVM and the What4 solver interface library. Our results demonstrate that dramatically increased compiler assurance can be achieved at moderate cost by building on existing tools. This paves the way to our ultimate goal of generating formal assurance arguments that are convincing to human auditors.

cs.PL↗

arXiv2026

CNnotator: LLM-Guided Memory Safety Annotation Synthesis

Memory safety errors account for a large proportion of security bugs in systems written in C; modern languages such as Java and Rust prevent such bugs because they are memory-safe by design. To migrate systems to safer languages or identify memory errors, we must first determine how legacy code manipulates memory. This information is only represented implicitly in such code. In many cases, memory usage patterns are merely tedious for humans to figure out, rather than truly difficult. In this work, we ask if large language models (LLMs) can perform this task by having them synthesize annotations representing memory usage as specifications in CN, a hybrid testing/verification tool. Our tool, CNnotator, uses LLMs to automatically generate and test CN specifications. We find that current models are able to generate CN specifications for small-to-medium C programs, with the OpenAI o3 reasoning model achieving a 90% success rate on first attempts and 97% overall success, while the chat model GPT-4o correctly annotates 65% of first attempts. These results suggest AI-assisted annotation is becoming practical for real-world C codebases.

cs.PL↗

arXiv2025

Macaw: A Machine Code Toolbox for the Busy Binary Analyst

When attempting to understand the behavior of an executable, a binary analyst can make use of many different techniques. These include program slicing, dynamic instrumentation, binary-level rewriting, symbolic execution, and formal verification, all of which can uncover insights into how a piece of machine code behaves. As a result, there is no one-size-fits-all binary analysis tool, so a binary analysis researcher will often combine several different tools. Sometimes, a researcher will even need to design new tools to study problems that existing frameworks are not well equipped to handle. Designing such tools from complete scratch is rarely time- or cost-effective, however, given the scale and complexity of modern ISAs. We present Macaw, a modular framework that makes it possible to rapidly build reliable binary analysis tools across a range of use cases. Statically typed functional programming techniques are used pervasively throughout Macaw -- these range from using functional optimization passes to encoding tricky architectural invariants at the type level to statically check correctness properties. The level of assurance that functional programming ideas afford us allow us to iterate rapidly on Macaw while still having confidence that the underlying semantics are correct. Over a decade of development, we have used Macaw to support an industrial research team in building tools for machine code-related tasks. As such, the name 'Macaw' refers not just to the framework, but also a suite of tools that are built on top of it. We describe Macaw in depth and describe the different static and dynamic analyses that it performs, many powered by an SMT-based symbolic execution engine. We put a particular focus on interoperability between machine code and higher-level languages, including binary lifting from x86 to LLVM, as well verifying the correctness of mixed C and assembly code.

cs.PL↗

arXiv2024

Crux, a Precise Verifier for Rust and Other Languages

We present Crux, a cross-language verification tool for Rust and C/LLVM. Crux targets bounded, intricate pieces of code that are difficult for humans to get right: for example, cryptographic modules and serializer / deserializer pairs. Crux builds on the same framework as the mature SAW-Cryptol toolchain, but Crux provides an interface where proofs are phrased as symbolic unit tests. Crux is designed for use in production environments, and has already seen use in industry. In this paper, we focus on Crux-MIR, our verification tool for Rust. Crux-MIR provides a bit-precise model of safe and unsafe Rust which can be used to check both inline properties about Rust code, and extensional equality to executable specifications written in Cryptol or in the hacspec dialect of Rust. Notably, Crux-MIR supports compositional reasoning, which is necessary to scale to even moderately complex proofs. We demonstrate Crux-MIR by verifying the Ring library implementations of SHA1 and SHA2 against pre-existing functional specifications. Crux is available at https://crux.galois.com.

cs.PL↗

arXiv2018

Compositional Verification of Compiler Optimisations on Relaxed Memory

A valid compiler optimisation transforms a block in a program without introducing new observable behaviours to the program as a whole. Deciding which optimisations are valid can be difficult, and depends closely on the semantic model of the programming language. Axiomatic relaxed models, such as C++11, present particular challenges for determining validity, because such models allow subtle effects of a block transformation to be observed by the rest of the program. In this paper we present a denotational theory that captures optimisation validity on an axiomatic model corresponding to a fragment of C++11. Our theory allows verifying an optimisation compositionally, by considering only the block it transforms instead of the whole program. Using this property, we realise the theory in the first push-button tool that can verify real-world optimisations under an axiomatic memory model.

cs.PL↗

arXiv2017

Proving Linearizability Using Partial Orders (Extended Version)

Linearizability is the commonly accepted notion of correctness for concurrent data structures. It requires that any execution of the data structure is justified by a linearization --- a linear order on operations satisfying the data structure's sequential specification. Proving linearizability is often challenging because an operation's position in the linearization order may depend on future operations. This makes it very difficult to incrementally construct the linearization in a proof. We propose a new proof method that can handle data structures with such future-dependent linearizations. Our key idea is to incrementally construct not a single linear order of operations, but a partial order that describes multiple linearizations satisfying the sequential specification. This allows decisions about the ordering of operations to be delayed, mirroring the behaviour of data structure implementations. We formalise our method as a program logic based on rely-guarantee reasoning, and demonstrate its effectiveness by verifying several challenging data structures: the Herlihy-Wing queue, the TS queue and the Optimistic set.

cs.PL↗

arXiv2015

Refining Existential Properties in Separation Logic Analyses

In separation logic program analyses, tractability is generally achieved by restricting invariants to a finite abstract domain. As this domain cannot vary, loss of information can cause failure even when verification is possible in the underlying logic. In this paper, we propose a CEGAR-like method for detecting spurious failures and avoiding them by refining the abstract domain. Our approach is geared towards discovering existential properties, e.g. "list contains value x". To diagnose failures, we use abduction, a technique for inferring command preconditions. Our method works backwards from an error, identifying necessary information lost by abstraction, and refining the forward analysis to avoid the error. We define domains for several classes of existential properties, and show their effectiveness on case studies adapted from Redis, Azureus and FreeRTOS.

cs.LO↗