MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gajjar, Jugal, Subramaniakuppusamy, Kamalasankari, Kachach, Noha El
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909796871962624
author Gajjar, Jugal
Subramaniakuppusamy, Kamalasankari
Kachach, Noha El
author_facet Gajjar, Jugal
Subramaniakuppusamy, Kamalasankari
Kachach, Noha El
contents The growing complexity of cyber threats and the limitations of traditional vulnerability detection tools necessitate novel approaches for securing software systems. We introduce MalCodeAI, a language-agnostic, multi-stage AI pipeline for autonomous code security analysis and remediation. MalCodeAI combines code decomposition and semantic reasoning using fine-tuned Qwen2.5-Coder-3B-Instruct models, optimized through Low-Rank Adaptation (LoRA) within the MLX framework, and delivers scalable, accurate results across 14 programming languages. In Phase 1, the model achieved a validation loss as low as 0.397 for functional decomposition and summarization of code segments after 200 iterations, 6 trainable layers, and a learning rate of 2 x 10^(-5). In Phase 2, for vulnerability detection and remediation, it achieved a best validation loss of 0.199 using the same number of iterations and trainable layers but with an increased learning rate of 4 x 10^(-5), effectively identifying security flaws and suggesting actionable fixes. MalCodeAI supports red-hat-style exploit tracing, CVSS-based risk scoring, and zero-shot generalization to detect complex, zero-day vulnerabilities. In a qualitative evaluation involving 15 developers, the system received high scores in usefulness (mean 8.06/10), interpretability (mean 7.40/10), and readability of outputs (mean 7.53/10), confirming its practical value in real-world development workflows. This work marks a significant advancement toward intelligent, explainable, and developer-centric software security solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2507_10898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning
Gajjar, Jugal
Subramaniakuppusamy, Kamalasankari
Kachach, Noha El
Cryptography and Security
Artificial Intelligence
Software Engineering
The growing complexity of cyber threats and the limitations of traditional vulnerability detection tools necessitate novel approaches for securing software systems. We introduce MalCodeAI, a language-agnostic, multi-stage AI pipeline for autonomous code security analysis and remediation. MalCodeAI combines code decomposition and semantic reasoning using fine-tuned Qwen2.5-Coder-3B-Instruct models, optimized through Low-Rank Adaptation (LoRA) within the MLX framework, and delivers scalable, accurate results across 14 programming languages. In Phase 1, the model achieved a validation loss as low as 0.397 for functional decomposition and summarization of code segments after 200 iterations, 6 trainable layers, and a learning rate of 2 x 10^(-5). In Phase 2, for vulnerability detection and remediation, it achieved a best validation loss of 0.199 using the same number of iterations and trainable layers but with an increased learning rate of 4 x 10^(-5), effectively identifying security flaws and suggesting actionable fixes. MalCodeAI supports red-hat-style exploit tracing, CVSS-based risk scoring, and zero-shot generalization to detect complex, zero-day vulnerabilities. In a qualitative evaluation involving 15 developers, the system received high scores in usefulness (mean 8.06/10), interpretability (mean 7.40/10), and readability of outputs (mean 7.53/10), confirming its practical value in real-world development workflows. This work marks a significant advancement toward intelligent, explainable, and developer-centric software security solutions.
title MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning
topic Cryptography and Security
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2507.10898