Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

Documenti analoghi

• TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code
  di: Sternfeld, Alexander, et al.
  Pubblicazione: (2025)
• Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability Detection
  di: Trad, Fouad, et al.
  Pubblicazione: (2025)
• ProSec: Fortifying Code LLMs with Proactive Security Alignment
  di: Xu, Xiangzhe, et al.
  Pubblicazione: (2024)
• From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting
  di: Vallez, Cyril, et al.
  Pubblicazione: (2025)
• From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting
  di: Liu, Shigang, et al.
  Pubblicazione: (2024)