SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward

• URL: http://arxiv.org/abs/2606.25195v1
• Date: Tue, 23 Jun 2026 21:39:05 GMT
• Title: SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward
• Abstract summary: This SoK systematizes the progress, pitfalls, and paths forward for AI secure code generation.<n>We show that secure-coding-principle understanding is a statistically strong predictor of code-level outcomes.<n>We identify concrete paths forward through principle-guided generation, evaluation, benchmarking, and agentic.
• Score: 18.590367120499394
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The increasing use of AI systems for code generation raises a central security question: what can today's models and coding agents actually do to produce secure code, where do they still fail, and what would move the field forward? Existing work has explored prompting, fine-tuning, reinforcement learning, and agentic workflows for secure code generation, but the field still lacks a systematic understanding of how these techniques improve security and why substantial failures persist. In this SoK, we systematize the progress, pitfalls, and paths forward for AI secure code generation. We introduce a three-level framework that measures models' natural-language understanding of secure coding principles, their code-level actuation of those principles during generation, and the knowledge--actuation gaps between the two. We instantiate this framework across models and coding agents on benchmarks covering both isolated function-level security and full web-application security. Our results show that secure-coding-principle understanding is a statistically strong predictor of code-level outcomes, including functional correctness, security, and joint functional-security correctness. Yet substantial knowledge--actuation gaps remain: models can recognize relevant security principles but still fail to translate them into secure and functional code. These findings offer a principle-centered account of where AI secure code generation stands today and identify concrete paths forward through principle-guided generation, evaluation, benchmarking, and agentic workflows.

Related papers

• SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization [50.71047638695205]
  Reasoning language models (RLMs) are increasingly used in programming.<n>Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabilities in generated code.<n>We present SecPI, a fine-tuning pipeline that teaches RLMs to internalize structured security reasoning.
  arXiv  Detail & Related papers  (2026-04-04T04:29:11Z)
• Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms [6.049331537822609]
  Large Language Models (LLMs) show remarkable capabilities in understanding natural language and generating complex code.<n>Research reveals that CodeLLMs frequently generate functionally correct yet insecure code, posing significant security risks.<n>We propose Secure Concept Steering for CodeLLMs (SCS-Code), which steers LLMs' internal representations toward secure and functional code output.
  arXiv  Detail & Related papers  (2026-03-11T18:28:06Z)
• Inference-Time Safety For Code LLMs Via Retrieval-Augmented Revision [3.983997834693767]
  Large Language Models (LLMs) are increasingly deployed for code generation in high-stakes software development.<n>LLMs cannot readily adapt to newly discovered vulnerabilities or changing security standards without retraining.<n>We present a principled approach to trustworthy code generation by design that operates as an inference-time safety mechanism.
  arXiv  Detail & Related papers  (2026-03-02T06:06:34Z)
• LLMs + Security = Trouble [5.235480194772795]
  "Fighting fire with fire" approach fails to address the long tail of security bugs.<n>We argue that stronger security guarantees can be obtained by enforcing security constraints during code generation.
  arXiv  Detail & Related papers  (2026-02-09T09:27:28Z)
• Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model [60.60587869092729]
  Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment.<n>We propose SecCoderX, an online reinforcement learning framework for functionality-preserving secure code generation.
  arXiv  Detail & Related papers  (2026-02-07T07:42:07Z)
• LLM Agents Should Employ Security Principles [60.03651084139836]
  This paper argues that the well-established design principles in information security should be employed when deploying Large Language Model (LLM) agents at scale.<n>We introduce AgentSandbox, a conceptual framework embedding these security principles to provide safeguards throughout an agent's life-cycle.
  arXiv  Detail & Related papers  (2025-05-29T21:39:08Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection [5.011290848820237]
  Existing Retrieval-Augmented Code Generation (RACG) systems largely overlook security, leading to substantial risks.<n>We propose a security-hardening framework for RACG systems, CodeGuarder, that shifts the paradigm from retrieving only functional code examples to incorporating both functional code and security knowledge.<n>Our framework constructs a security knowledge base from real-world vulnerability databases, including secure code samples and root cause annotations.
  arXiv  Detail & Related papers  (2025-04-23T05:27:27Z)
• CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion [117.178835165855]
  This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs. Our studies reveal a new and universal safety vulnerability of these models against code input. We find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization.
  arXiv  Detail & Related papers  (2024-03-12T17:55:38Z)
• CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models [58.27254444280376]
  Large language models (LLMs) for automatic code generation have achieved breakthroughs in several programming tasks. Training data for these models is usually collected from the Internet (e.g., from open-source repositories) and is likely to contain faults and security vulnerabilities. This unsanitized training data can cause the language models to learn these vulnerabilities and propagate them during the code generation procedure.
  arXiv  Detail & Related papers  (2023-02-08T11:54:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.