This paper presents a novel approach integrating Large Language Models (LLMs) with Formal Verification for automatic software vulnerability repair. Initially, we employ Bounded Model Checking (BMC) to identify vulnerabilities and extract counterexamples. Mathematical proofs and the stack trace of the vulnerabilities support these counterexamples. Using a specially designed prompt, we combine the source code with the identified vulnerability, including its stack trace and counterexample that specifies the line number and error type. This combined information is then fed into an LLM, which is instructed to attempt to fix the code. The new code is subsequently verified again using BMC to ensure the fix succeeded. We present the ESBMC-AI framework as a proof of concept, leveraging the well-recognized and industry-adopted Efficient SMT-based Context-Bounded Model Checker (ESBMC) and a pre-trained transformer model to detect and fix errors in C programs, particularly in critical software components. We evaluated our approach on 50, 000 C programs randomly selected from the FormAI dataset with their respective vulnerability classifications. Our results demonstrate ESBMC-AI’s capability to automate the detection and repair of issues such as buffer overflow, arithmetic overflow, and pointer dereference failures with high accuracy. ESBMC-AI is a pioneering initiative, integrating LLMs with BMC techniques, offering potential integration into the continuous integration and deployment (CI/CD) process within the software development lifecycle.

Bug reproduction is becoming an important task in the security analysis of Solidity smart contracts. By simulating attacks, developers and auditors can better understand how a vulnerability is triggered in practice. To reproduce a bug, one often needs to define an attacker contract and a specific sequence of interactions that exploit the vulnerability. However, in smart contracts, there are rarely automated tools that can generate such contracts and sequences and validate their correctness. Existing security tools, such as formal verifiers, are effective at detecting bugs, but they are not designed for bug reproduction. They often omit execution traces or produce incomplete ones. Moreover, their reports rarely reflect the behaviour patterns of attacker contracts. This gap motivates our work. We propose VeriExploit, a framework that combines formal methods and large language models to automatically generate, validate, and refine reproduction contracts and execution steps. Given a vulnerable contract and its counterexample, VeriExploit produces a contract that re-triggers the same bug and outputs a concrete trace showing how the exploit works. Experiments show that VeriExploit is effective at automating bug reproduction, achieving a success rate of 85.60% on our benchmark dataset.