AI Code Generators for Security: Friend or Foe?

Abstract

Recent advances of artificial intelligence (AI) code generators are opening new opportunities in software security research, including misuse by malicious actors. We review use cases for AI code generators for security and introduce an evaluation benchmark.

Dataset available at: https://github.com/dessertlab/violent-python

References in corpus (2)

• LIMA: Less Is More for Alignment
• Can We Generate Shellcodes via Natural Language? An Empirical Study