Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Baby, Maksuda Bilkis, Shah, Khushika, Liang, Naiyue, Zhang, Lei
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916066584690688
author Baby, Maksuda Bilkis
Shah, Khushika
Liang, Naiyue
Zhang, Lei
author_facet Baby, Maksuda Bilkis
Shah, Khushika
Liang, Naiyue
Zhang, Lei
contents Credential leakage in public source code repositories poses a critical security threat, with over 23.8 million 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. We propose a three-class classification framework that explicitly models placeholder or weak credentials as a distinct class, leveraging CodeBERT-based semantic understanding combined with character-level pattern recognition. We evaluate our approach on a newly constructed dataset of 9,426 samples spanning 10 programming languages. Our model achieves a Matthews Correlation Coefficient of 0.86 and a macro F1-score of 0.90, achieving 93% recall and 89% precision for genuine credential leaks while reducing high severity alerts by 33.0% (from 373 to 250) without sacrificing security coverage. Compared to prior character-level approaches, our method improves placeholder or weak credential detection from 54% to 81% F1-score while maintaining strong cross language generalization, with 9 of 10 languages achieving F1 above 0.80 under leave-one-language-out evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_31520
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection
Baby, Maksuda Bilkis
Shah, Khushika
Liang, Naiyue
Zhang, Lei
Software Engineering
Artificial Intelligence
Cryptography and Security
Credential leakage in public source code repositories poses a critical security threat, with over 23.8 million 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. We propose a three-class classification framework that explicitly models placeholder or weak credentials as a distinct class, leveraging CodeBERT-based semantic understanding combined with character-level pattern recognition. We evaluate our approach on a newly constructed dataset of 9,426 samples spanning 10 programming languages. Our model achieves a Matthews Correlation Coefficient of 0.86 and a macro F1-score of 0.90, achieving 93% recall and 89% precision for genuine credential leaks while reducing high severity alerts by 33.0% (from 373 to 250) without sacrificing security coverage. Compared to prior character-level approaches, our method improves placeholder or weak credential detection from 54% to 81% F1-score while maintaining strong cross language generalization, with 9 of 10 languages achieving F1 above 0.80 under leave-one-language-out evaluation.
title Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection
topic Software Engineering
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2605.31520