DeVAIC: A Tool for Security Assessment of AI-generated Code

• URL: http://arxiv.org/abs/2404.07548v2
• Date: Mon, 2 Sep 2024 10:27:14 GMT
• Title: DeVAIC: A Tool for Security Assessment of AI-generated Code
• Authors: Domenico Cotroneo, Roberta De Luca, Pietro Liguori,
• Abstract summary: DeVAIC (Detection of Vulnerabilities in AI-generated Code) is a tool to evaluate the security of AI-generated Python code.
• Score: 5.383910843560784
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Context: AI code generators are revolutionizing code writing and software development, but their training on large datasets, including potentially untrusted source code, raises security concerns. Furthermore, these generators can produce incomplete code snippets that are challenging to evaluate using current solutions. Objective: This research work introduces DeVAIC (Detection of Vulnerabilities in AI-generated Code), a tool to evaluate the security of AI-generated Python code, which overcomes the challenge of examining incomplete code. Method: We followed a methodological approach that involved gathering vulnerable samples, extracting implementation patterns, and creating regular expressions to develop the proposed tool. The implementation of DeVAIC includes a set of detection rules based on regular expressions that cover 35 Common Weakness Enumerations (CWEs) falling under the OWASP Top 10 vulnerability categories. Results: We utilized four popular AI models to generate Python code, which we then used as a foundation to evaluate the effectiveness of our tool. DeVAIC demonstrated a statistically significant difference in its ability to detect security vulnerabilities compared to the state-of-the-art solutions, showing an F1 Score and Accuracy of 94% while maintaining a low computational cost of 0.14 seconds per code snippet, on average. Conclusions: The proposed tool provides a lightweight and efficient solution for vulnerability detection even on incomplete code.

Related papers

• 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)
• Impact of Code Transformation on Detection of Smart Contract Vulnerabilities [0.0]
  This paper presents a method for improving the quantity and quality of smart contract vulnerability datasets. The approach centers around semantic-preserving code transformation, a technique that modifies the source code structure without altering its semantic meaning. The improved results show that many newly created vulnerabilities can bypass tools and the false reporting rate goes up to 100%.
  arXiv  Detail & Related papers  (2024-10-29T03:08:25Z)
• The Vulnerability Is in the Details: Locating Fine-grained Information of Vulnerable Code Identified by Graph-based Detectors [33.395068754566935]
  VULEXPLAINER is a tool for locating vulnerability-critical code lines from coarse-level vulnerable code snippets. It can flag the vulnerability-triggering code statements with an accuracy of around 90% against eight common C/C++ vulnerabilities.
  arXiv  Detail & Related papers  (2024-01-05T10:15:04Z)
• Automating the Correctness Assessment of AI-generated Code for Security Contexts [8.009107843106108]
  We propose a fully automated method, named ACCA, to evaluate the correctness of AI-generated code for security purposes. We use ACCA to assess four state-of-the-art models trained to generate security-oriented assembly code. Our experiments show that our method outperforms the baseline solutions and assesses the correctness of the AI-generated code similar to the human-based evaluation.
  arXiv  Detail & Related papers  (2023-10-28T22:28:32Z)
• Zero-Shot Detection of Machine-Generated Codes [83.0342513054389]
  This work proposes a training-free approach for the detection of LLMs-generated codes. We find that existing training-based or zero-shot text detectors are ineffective in detecting code. Our method exhibits robustness against revision attacks and generalizes well to Java codes.
  arXiv  Detail & Related papers  (2023-10-08T10:08:21Z)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)
• 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)
• DCDetector: An IoT terminal vulnerability mining system based on distributed deep ensemble learning under source code representation [2.561778620560749]
  The goal of the research is to intelligently detect vulnerabilities in source codes of high-level languages such as C/C++. This enables us to propose a code representation of sensitive sentence-related slices of source code, and to detect vulnerabilities by designing a distributed deep ensemble learning model. Experiments show that this method can reduce the false positive rate of traditional static analysis and improve the performance and accuracy of machine learning.
  arXiv  Detail & Related papers  (2022-11-29T14:19:14Z)
• VELVET: a noVel Ensemble Learning approach to automatically locate VulnErable sTatements [62.93814803258067]
  This paper presents VELVET, a novel ensemble learning approach to locate vulnerable statements in source code. Our model combines graph-based and sequence-based neural networks to successfully capture the local and global context of a program graph. VELVET achieves 99.6% and 43.6% top-1 accuracy over synthetic data and real-world data, respectively.
  arXiv  Detail & Related papers  (2021-12-20T22:45:27Z)
• Software Vulnerability Detection via Deep Learning over Disaggregated Code Graph Representation [57.92972327649165]
  This work explores a deep learning approach to automatically learn the insecure patterns from code corpora. Because code naturally admits graph structures with parsing, we develop a novel graph neural network (GNN) to exploit both the semantic context and structural regularity of a program.
  arXiv  Detail & Related papers  (2021-09-07T21:24:36Z)
• Multi-context Attention Fusion Neural Network for Software Vulnerability Identification [4.05739885420409]
  We propose a deep learning model that learns to detect some of the common categories of security vulnerabilities in source code efficiently. The model builds an accurate understanding of code semantics with a lot less learnable parameters. The proposed AI achieves 98.40% F1-score on specific CWEs from the benchmarked NIST SARD dataset.
  arXiv  Detail & Related papers  (2021-04-19T11:50:36Z)

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.