Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation

• URL: http://arxiv.org/abs/2502.03233v1
• Date: Wed, 05 Feb 2025 14:49:12 GMT
• Title: Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation
• Authors: Bo Lin, Shangwen Wang, Liqian Chen, Xiaoguang Mao,
• Abstract summary: This paper presents the first comprehensive study on the security risks associated with RACG systems.<n>It focuses on how vulnerable code in the knowledge base compromises the security of generated code.<n>Our findings highlight the significant threat of knowledge base poisoning, where even a single poisoned code example can compromise up to 48% of generated code.
• Score: 4.907610470063863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The integration of Large Language Models (LLMs) into software development has revolutionized the field, particularly through the use of Retrieval-Augmented Code Generation (RACG) systems that enhance code generation with information from external knowledge bases. However, the security implications of RACG systems, particularly the risks posed by vulnerable code examples in the knowledge base, remain largely unexplored. This risk is particularly concerning given that public code repositories, which often serve as the sources for knowledge base collection in RACG systems, are usually accessible to anyone in the community. Malicious attackers can exploit this accessibility to inject vulnerable code into the knowledge base, making it toxic. Once these poisoned samples are retrieved and incorporated into the generated code, they can propagate security vulnerabilities into the final product. This paper presents the first comprehensive study on the security risks associated with RACG systems, focusing on how vulnerable code in the knowledge base compromises the security of generated code. We investigate the LLM-generated code security across different settings through extensive experiments using four major LLMs, two retrievers, and two poisoning scenarios. Our findings highlight the significant threat of knowledge base poisoning, where even a single poisoned code example can compromise up to 48% of generated code. Our findings provide crucial insights into vulnerability introduction in RACG systems and offer practical mitigation recommendations, thereby helping improve the security of LLM-generated code in future works.

Related papers

• 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. 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. 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)
• A Comprehensive Study of LLM Secure Code Generation [19.82291066720634]
  Previous research primarily relies on a single static analyzer, CodeQL, to detect vulnerabilities in generated code. We apply both security inspection and functionality validation to the same generated code and evaluate these two aspects together. Our study reveals that existing techniques often compromise the functionality of generated code to enhance security.
  arXiv  Detail & Related papers  (2025-03-18T20:12:50Z)
• RedCode: Risky Code Execution and Generation Benchmark for Code Agents [50.81206098588923]
  RedCode is a benchmark for risky code execution and generation. RedCode-Exec provides challenging prompts that could lead to risky code execution. RedCode-Gen provides 160 prompts with function signatures and docstrings as input to assess whether code agents will follow instructions.
  arXiv  Detail & Related papers  (2024-11-12T13:30:06Z)
• HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data [60.75578581719921]
  Large language models (LLMs) have shown great potential for automatic code generation. Recent studies highlight that many LLM-generated code contains serious security vulnerabilities. We introduce HexaCoder, a novel approach to enhance the ability of LLMs to generate secure codes.
  arXiv  Detail & Related papers  (2024-09-10T12:01:43Z)
• Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval [20.959848710829878]
  Large language models (LLMs) have brought significant advancements to code generation and code repair. However, their training using unsanitized data from open-source repositories, like GitHub, raises the risk of inadvertently propagating security vulnerabilities. We aim to present a comprehensive study aimed at precisely evaluating and enhancing the security aspects of code LLMs.
  arXiv  Detail & Related papers  (2024-07-02T16:13:21Z)
• "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models [74.05368440735468]
  Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases.
  arXiv  Detail & Related papers  (2024-06-26T05:36:23Z)
• On Security Weaknesses and Vulnerabilities in Deep Learning Systems [32.14068820256729]
  We specifically look into deep learning (DL) framework and perform the first systematic study of vulnerabilities in DL systems. We propose a two-stream data analysis framework to explore vulnerability patterns from various databases. We conducted a large-scale empirical study of 3,049 DL vulnerabilities to better understand the patterns of vulnerability and the challenges in fixing them.
  arXiv  Detail & Related papers  (2024-06-12T23:04:13Z)
• 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)
• Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation [24.668682498171776]
  Large language models (LLMs) have brought significant advancements to code generation, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, introduces the risk of inadvertently propagating security vulnerabilities. This paper presents a comprehensive study focused on evaluating and enhancing code LLMs from a software security perspective.
  arXiv  Detail & Related papers  (2023-10-25T00:32:56Z)
• Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI [76.28956947107372]
  Covertly unsafe text is an area of particular interest, as such text may arise from everyday scenarios and are challenging to detect as harmful. We propose FARM, a novel framework leveraging external knowledge for trustworthy rationale generation in the context of safety. Our experiments show that FARM obtains state-of-the-art results on the SafeText dataset, showing absolute improvement in safety classification accuracy by 5.9%.
  arXiv  Detail & Related papers  (2022-12-19T17:51:47Z)
• A Hierarchical Deep Neural Network for Detecting Lines of Codes with Vulnerabilities [6.09170287691728]
  Software vulnerabilities, caused by unintentional flaws in source codes, are the main root cause of cyberattacks. We propose a deep learning approach to detect vulnerabilities from their LLVM IR representations based on the techniques that have been used in natural language processing.
  arXiv  Detail & Related papers  (2022-11-15T21:21:27Z)
• Dos and Don'ts of Machine Learning in Computer Security [74.1816306998445]
  Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance. We identify common pitfalls in the design, implementation, and evaluation of learning-based security systems. We propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible.
  arXiv  Detail & Related papers  (2020-10-19T13:09:31Z)

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.