Leakage-Aware Cross-Dataset Evaluation of Prompt Injection Detection Using Classical Machine Learning and Transformer Models

Abstract

The widespread adoption of systems based on Large Language Models has made the reliable detection of prompt injection attacks a critical requirement. However, high performance achieved on training and test splits generated from the same data source does not guarantee that models can generalize to prompts from different sources. In this study, a leak-aware cross-dataset evaluation framework is presented to examine the robustness of classical machine learning and Transformer-based prompt injection

Categories

Framework mappings

Suggested from the entry's categories.

@article{kilim2026leakageaware,
  title = {{Leakage-Aware Cross-Dataset Evaluation of Prompt Injection Detection Using Classical Machine Learning and Transformer Models}},
  author = {Oğuzhan Kilim},
  year = {2026},
  month = sep,
  journal = {Yalvaç akademi dergisi},
  doi = {10.57120/yalvac.2001116},
  url = {https://www.semanticscholar.org/paper/9927bbc6c11def4346dc8112ca690825efde1f06}
}