AI RESEARCH
Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection
arXiv CS.AI
•
ArXi:2605.31520v1 Announce Type: cross Credential leakage in public source code repositories poses a critical security threat, with over 23.8M secrets exposed in 2024 alone. Existing detection tools suffer from high false-positive rates because rigid pattern matching and binary classification schemes fail to distinguish genuine credentials from placeholder or weak credentials.