# Enhancing Reliability in LLM-Based Secure Code Generation

arXiv: https://arxiv.org/abs/2605.24300 · HTML: https://mlsanity.com/paper/2605.24300/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 30 of 35)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks](https://mlsanity.com/paper/2312.12575/) (2023)
- [Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants](https://mlsanity.com/paper/2208.09727/) (2022)
- [Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT](https://mlsanity.com/paper/2304.10778/) (2023)
- [Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?](https://mlsanity.com/paper/2204.04741/) (2022)
- [Why Does the Effective Context Length of LLMs Fall Short?](https://mlsanity.com/paper/2410.18745/) (2024)
- [LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations](https://mlsanity.com/paper/2303.09384/) (2023)
- [CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation](https://mlsanity.com/paper/2501.08200/) (2025)
- [BaxBench: Can LLMs Generate Correct and Secure Backends?](https://mlsanity.com/paper/2502.11844/) (2025)
- [SALLM: Security Assessment of Generated Code](https://mlsanity.com/paper/2311.00889/) (2023)
- [Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study](https://mlsanity.com/paper/2310.02059/) (2023)
- [Prompting Techniques for Secure Code Generation: A Systematic Investigation](https://mlsanity.com/paper/2407.07064/) (2024)
- [Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities](https://mlsanity.com/paper/2402.17230/) (2024)
- [Using AI Assistants in Software Development: A Qualitative Study on Security Practices and Concerns](https://mlsanity.com/paper/2405.06371/) (2024)
- [Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications](https://mlsanity.com/paper/2503.01245/) (2025)
- [How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models](https://mlsanity.com/paper/2404.18353/) (2024)
- [PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)](https://mlsanity.com/paper/2409.12699/) (2024)
- [Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis](https://mlsanity.com/paper/2502.01853/) (2025)
- [Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection](https://mlsanity.com/paper/2504.16429/) (2025)
- [A User-centered Security Evaluation of Copilot](https://mlsanity.com/paper/2308.06587/) (2023)
- [Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models](https://mlsanity.com/paper/2502.06039/) (2025)
- [Rethinking the Evaluation of Secure Code Generation](https://mlsanity.com/paper/2503.15554/) (2025)
- [DeVAIC: A Tool for Security Assessment of AI-generated Code](https://mlsanity.com/paper/2404.07548/) (2024)
- [RESCUE: Retrieval Augmented Secure Code Generation](https://mlsanity.com/paper/2510.18204/) (2025)

## Built on by (most cited first, 2 of 2)

- [Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline](https://mlsanity.com/paper/2608.16187/) (2026)
- [Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis](https://mlsanity.com/paper/2610.08405/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are widely used for code generation, but their security reliability remains inconsistent across languages and prompting strategies. Existing prompt engineering improves functional correctness but rarely ensures consistent security outcomes. We introduce the textitMitigation-Aware Chain-of-Thought (MA-CoT) framework, which embeds task-specific CWE mitigation guidance and language-aware safeguards to reduce recurring vulnerabilities in generated code. We evaluate MA-CoT across three LLMs (gpt-5, claude-4.5, gemini-2.5), three programming languages (C, Java, Python), and four prompting strategies (Vanilla, Zero-shot, CoT, MA-CoT) on a 200-task primary dataset, with external validation on LLMSecEval. Using static analysis with expert validation, MA-CoT reduces total security findings from 92 to 39 (57.6%) on the primary dataset and from 73 to 4 (94.5%) on LLMSecEval. High-severity findings (Blocker + Critical) drop from 90 to 39 (56.7%) and from 45 to 2 (95.6%), respectively. Across both datasets, MA-CoT is the only strategy that consistently improves security reliability; Zero-shot and CoT are less reliable and may increase vulnerability, especially in C. We further introduce a strict layered attribution of vulnerability drivers (language-core vs. stack layers) and show that residual risk concentrates in hardening-oriented patterns (e.g., OS- and toolchain-dependent), motivating secure-by-construction primitives alongside prompting.