Related papers: ConVer: Using Contracts and Loop Invariant Synthes…

In this work, we systematically expose and measure the inconsistency and knowledge gaps of Large Language Models (LLMs). Specifically, we propose an automated testing framework (called KonTest) which leverages a knowledge graph to construct…

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…

Program verification relies on loop invariants, yet automatically discovering strong invariants remains a long-standing challenge. We investigate whether large language models (LLMs) can accelerate program verification by generating useful…

Automated detection of software vulnerabilities is critical for enhancing security, yet existing methods often struggle with the complexity and diversity of modern codebases. In this paper, we introduce EnStack, a novel ensemble stacking…

Frama-C is a software analysis framework that provides a common infrastructure and a common behavioral specification language to plugins that implement various static and dynamic analyses of C programs. Most plugins do not support…

Large Language Models (LLMs) have emerged as promising tools for malware detection by analyzing code semantics, identifying vulnerabilities, and adapting to evolving threats. However, their reliability under adversarial compiler-level…

The significant increase in software production, driven by the acceleration of development cycles over the past two decades, has led to a steady rise in software vulnerabilities, as shown by statistics published yearly by the CVE program.…

Compositional verification algorithms are well-studied in the context of model checking. Properly selecting components for verification is important for efficiency, yet has received comparatively less attention. In this paper, we address…

Formal theorem proving (FTP) has emerged as a critical foundation for evaluating the reasoning capabilities of large language models, enabling automated verification of mathematical proofs at scale. However, progress has been constrained by…

In deductive verification and software model checking, dealing with certain specification language constructs can be problematic when the back-end solver is not sufficiently powerful or lacks the required theories. One way to deal with this…

Formal verification provides mathematical guarantees that a software is correct. Design-level verification tools ensure software specifications are correct, but they do not expose defects in actual implementations. For this purpose,…

Program analysis is on the brink of mainstream in embedded systems development. Formal verification of behavioural requirements, finding runtime errors and automated test case generation are some of the most common applications of automated…

Semiconductor companies have increasingly adopted a methodology that starts with a system-level design specification in C/C++/SystemC. This model is extensively simulated to ensure correct functionality and performance. Later, a Register…

Verifying hardware designs in embedded systems is crucial but often labor-intensive and time-consuming. While existing solutions have improved automation, they frequently rely on unrealistic assumptions. To address these challenges, we…

Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing returns from parameter scaling. While recent multi-step…

We introduce DafnyBench, the largest benchmark of its kind for training and evaluating machine learning systems for formal software verification. We test the ability of LLMs such as GPT-4 and Claude 3 to auto-generate enough hints for the…

Large language models have achieved remarkable success on final-answer mathematical problems, largely due to the ease of applying reinforcement learning with verifiable rewards. However, the reasoning underlying these solutions is often…

Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recently demonstrated their potential for enhancing the degree of automation in formal…

Bounded model checking is among the most efficient techniques for the automatic verification of concurrent programs. However, encoding all possible interleavings often requires a huge and complex formula, which significantly limits the…

Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM…