Detecting Prompt Injection Attacks Against Application Using Classifiers

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shaheer, Safwan, Islam, G. M. Refatul, Hamid, Mohammad Rafid, Khan, Md. Abrar Faiaz, Faruk, Md. Omar, Nur, Yaseen
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914200697176064
author Shaheer, Safwan
Islam, G. M. Refatul
Hamid, Mohammad Rafid
Khan, Md. Abrar Faiaz
Faruk, Md. Omar
Nur, Yaseen
author_facet Shaheer, Safwan
Islam, G. M. Refatul
Hamid, Mohammad Rafid
Khan, Md. Abrar Faiaz
Faruk, Md. Omar
Nur, Yaseen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12583
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Detecting Prompt Injection Attacks Against Application Using Classifiers
Shaheer, Safwan
Islam, G. M. Refatul
Hamid, Mohammad Rafid
Khan, Md. Abrar Faiaz
Faruk, Md. Omar
Nur, Yaseen
Cryptography and Security
Artificial Intelligence
D.4.6; I.2.7
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.
title Detecting Prompt Injection Attacks Against Application Using Classifiers
topic Cryptography and Security
Artificial Intelligence
D.4.6; I.2.7
url https://arxiv.org/abs/2512.12583