# Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective

arXiv: https://arxiv.org/abs/2505.10494 · HTML: https://mlsanity.com/paper/2505.10494/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models](https://mlsanity.com/paper/2312.04724/) (2023)
- [The Art, Science, and Engineering of Fuzzing: A Survey](https://mlsanity.com/paper/1812.00140/) (2018)
- [LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations](https://mlsanity.com/paper/2303.09384/) (2023)
- [No Need to Lift a Finger Anymore? Assessing the Quality of Code Generation by ChatGPT](https://mlsanity.com/paper/2308.04838/) (2023)
- [CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation](https://mlsanity.com/paper/2311.08588/) (2023)
- [AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing](https://mlsanity.com/paper/2409.10737/) (2024)
- [Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation](https://mlsanity.com/paper/2310.16263/) (2023)
- [Full-speed Fuzzing: Reducing Fuzzing Overhead through Coverage-guided Tracing](https://mlsanity.com/paper/1812.11875/) (2018)

## Built on by (most cited first, 6 of 6)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code](https://mlsanity.com/paper/2508.18106/) (2025)
- [AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming](https://mlsanity.com/paper/2510.08329/) (2025)
- [Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices](https://mlsanity.com/paper/2510.09682/) (2025)
- [A Quasi-Experimental Developer Study of Security Training in LLM-Assisted Web Application Development](https://mlsanity.com/paper/2604.17763/) (2026)
- [The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting](https://mlsanity.com/paper/2607.23710/) (2026)

## Abstract (arXiv)

Code security and usability are both essential for various coding assistant applications driven by large language models (LLMs). Current code security benchmarks focus solely on single evaluation task and paradigm, such as code completion and generation, lacking comprehensive assessment across dimensions like secure code generation, vulnerability repair and discrimination. In this paper, we first propose CoV-Eval, a multi-task benchmark covering various tasks such as code completion, vulnerability repair, vulnerability detection and classification, for comprehensive evaluation of LLM code security. Besides, we developed VC-Judge, an improved judgment model that aligns closely with human experts and can review LLM-generated programs for vulnerabilities in a more efficient and reliable way. We conduct a comprehensive evaluation of 20 proprietary and open-source LLMs. Overall, while most LLMs identify vulnerable codes well, they still tend to generate insecure codes and struggle with recognizing specific vulnerability types and performing repairs. Extensive experiments and qualitative analyses reveal key challenges and optimization directions, offering insights for future research in LLM code security.