PulseAugur
EN
LIVE 07:07:53

LLMs automate smart contract vulnerability injection for testing tools

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a method to automatically inject vulnerabilities into smart contracts using large language models (LLMs). This approach aims to create datasets for testing vulnerability detection tools, addressing the scarcity of manually built datasets. The study successfully generated 32 validated vulnerable contracts across 25 types by applying LLMs to real-world contracts, though it highlighted challenges with LLM non-determinism and semantic preservation. The generated dataset was then used to evaluate three static analyzers, revealing their complementary coverage profiles. AI

IMPACT Enables more robust testing of smart contract security tools, potentially leading to safer blockchain applications.

RANK_REASON Academic paper detailing a new method for generating datasets for smart contract security. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

LLMs automate smart contract vulnerability injection for testing tools

How we ranked this

Signal score
24 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper detailing a new method for generating datasets for smart contract security. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Luca Migliaccio, Roberto Natella, Naghmeh Ivaki, Nuno Laranjeiro, Marco Vieira ·

    Automated Vulnerability Injection in Smart Contracts Using Large Language Models

    arXiv:2609.02624v1 Announce Type: cross Abstract: Assessing vulnerability detection tools for smart contracts requires datasets with known ground truth, yet such datasets are scarce and difficult to build by hand. We propose an approach that uses Large Language Models (LLMs) to a…

RELATED ENTITIES

RELATED TOPICS