Jadhav, Gaurav and Singh, Amit Kumar and Khanam, Zeba and Hercock, Robert (2025) A Novel GNN-based Approach for Detection of Prompt Injection Attacks. In: IEEE International Conference on Cyber Security and Resilience (CSR), 2025-08-04 - 2025-08-06, Crete, Greece. (In Press)
Jadhav, Gaurav and Singh, Amit Kumar and Khanam, Zeba and Hercock, Robert (2025) A Novel GNN-based Approach for Detection of Prompt Injection Attacks. In: IEEE International Conference on Cyber Security and Resilience (CSR), 2025-08-04 - 2025-08-06, Crete, Greece. (In Press)
Jadhav, Gaurav and Singh, Amit Kumar and Khanam, Zeba and Hercock, Robert (2025) A Novel GNN-based Approach for Detection of Prompt Injection Attacks. In: IEEE International Conference on Cyber Security and Resilience (CSR), 2025-08-04 - 2025-08-06, Crete, Greece. (In Press)
Abstract
Prompt injection attacks manipulate language model inputs to bypass intended constraints, extract sensitive information, or generate misleading responses, posing a significant security risk in real-world applications. To address this challenge, we propose a Graph Neural Network (GNN)- based approach that integrates sentiment features and Bidirectional Encoder Representations from Transformers (BERT) embeddings to effectively detect malicious prompt injections. By transforming textual data into structured graph representations, our approach captures both semantic and contextual relationships that conventional models often overlook. We evaluate our approach against traditional machine learning techniques, including Random Forest, Logistic Regression, and XGBoost, demonstrating its superior performance. Experimental results show that our approach achieves a high detection accuracy of 98.70% and an F1-score of 0.9799, significantly outperforming conventional methods. Additionally, we provide an in-depth analysis of computational efficiency, highlighting the trade-offs between detection effectiveness and model complexity, ensuring a practical balance between security and performance.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Published proceedings: _not provided_ |
Uncontrolled Keywords: | GNN, Random Forest, GPT-4, Prompt Injection, Neural Network, Large Language Model, BERT, Semantic analysis, Sentiment Analysis |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 02 May 2025 13:55 |
Last Modified: | 02 May 2025 13:56 |
URI: | http://repository.essex.ac.uk/id/eprint/40752 |
Available files
Filename: A_Novel_GNN_based_Approach_for_Detection_of_Prompt_Injection_Attacks (1).pdf
Embargo Date: 7 August 2025