Automated Vulnerability Injection in Smart Contracts Using Large Language Models
Source
Luca Migliaccio, Roberto Natella, Naghmeh Ivaki, Nuno Laranjeiro, Marco Vieira
Author
Luca Migliaccio, Roberto Natella, Naghmeh Ivaki, Nuno Laranjeiro, Marco Vieira
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
Generating ground-truth vulnerable code with LLMs works, but only about one in six candidates survives validation, and mostly in simple contracts with localized syntax patterns. Budget for heavy filtering if you build evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → datasets this way.
articleAgentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration TestingIsrat Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Jakir Hossain, M. F. Mridha
articleCode Health in LLM-Based Test Generation: Effectiveness and Token EfficiencyFreya Wirdemann, Markus Borg, Nadim Hagatulah, Adam Tornhill
articleBreaking Models to Test the Judge: A Mutation Testing Approach for Semantic Evaluators of Domain Class DiagramsKevin Delcourt, Meriem Ben Chaaben, Abdelhamid Rouatbi, Luciano Marchezan, Houari Sahraoui