defense arXiv Dec 14, 2025 · Dec 2025
Safwan Shaheer, G. M. Refatul Islam, Mohammad Rafid Hamid et al. · BRAC University
Trains LSTM, FNN, Random Forest, and Naive Bayes classifiers to detect prompt injection attacks in LLM-integrated web applications
Prompt Injection nlp
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.
llm rnn traditional_ml BRAC University
ML Security Papers