Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox

May 19, 2025 Β· Declared Dead Β· πŸ› International Symposium on Technology and Society

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Shivani Shukla, Himanshu Joshi, Romilla Syed arXiv ID 2506.11022 Category cs.SE: Software Engineering Cross-listed cs.AI, cs.CL, cs.CR, cs.LG Citations 4 Venue International Symposium on Technology and Society Last Checked 4 months ago
Abstract
The rapid adoption of Large Language Models(LLMs) for code generation has transformed software development, yet little attention has been given to how security vulnerabilities evolve through iterative LLM feedback. This paper analyzes security degradation in AI-generated code through a controlled experiment with 400 code samples across 40 rounds of "improvements" using four distinct prompting strategies. Our findings show a 37.6% increase in critical vulnerabilities after just five iterations, with distinct vulnerability patterns emerging across different prompting approaches. This evidence challenges the assumption that iterative LLM refinement improves code security and highlights the essential role of human expertise in the loop. We propose practical guidelines for developers to mitigate these risks, emphasizing the need for robust human validation between LLM iterations to prevent the paradoxical introduction of new security issues during supposedly beneficial code "improvements".
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted