Score: 0

Detecting Prompt Injection Attacks Against Application Using Classifiers

Published: December 14, 2025 | arXiv ID: 2512.12583v1

By: Safwan Shaheer , G. M. Refatul Islam , Mohammad Rafid Hamid and more

Potential Business Impact:

Stops bad instructions from breaking computer programs.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions corpus and trains several classifiers, including LSTM, feed forward neural networks, Random Forest, and Naive Bayes, to detect malicious prompts in LLM integrated web applications. The proposed approach improves prompt injection detection and mitigation, helping protect targeted applications and systems.

Page Count
8 pages

Category
Computer Science:
Cryptography and Security