Back
Tonella_2025_Springer_s10664-025-10743-w
Journal article

Evaluating and improving the robustness of security attack detectors generated by LLMs

Show more…
  • 2025
Published in:
  • Empirical Software Engineering. - 2025, vol. 31, no. 2, p. 35
Large Language Models
Code security
Attack detection
Retrieval Augmented Generation
English Large Language Models (LLMs) are increasingly used in software development to generate functions, such as attack detectors, that implement security requirements. A key challenge is ensuring the LLMs have enough knowledge to address specific security requirements, such as information about existing attacks. For this, we propose an approach integrating Retrieval Augmented Generation (RAG) and Self-Ranking into the LLM pipeline. RAG enhances the robustness of the output by incorporating external knowledge sources, while the Self-Ranking technique, inspired by the concept of Self-Consistency, generates multiple reasoning paths and creates ranks to select the most robust detector. Our extensive empirical study targets code generated by LLMs to detect two prevalent injection attacks in web security: Cross-Site Scripting (XSS) and SQL injection (SQLi). Results show a significant improvement in detection performance while employing RAG and Self-Ranking, with an increase of up to 71%pt (on average 37%pt) and up to 43%pt (on average 6%pt) in the F2-Score for XSS and SQLi detection, respectively.
Collections
Language
  • English
Classification
Computer science and technology
License
CC BY
Open access status
hybrid
Identifiers
Persistent URL
https://n2t.net/ark:/12658/srd1333995
Statistics
Document views: 6 File downloads:
  • Tonella_2025_Springer_s10664-025-10743-w: 10