Advanced security testing using a cyber‐attack forecasting model: A case study of financial institutions. Issue 11 (8th August 2022)

• Record Type: Journal Article
• Authors: Qasaimeh, Malik; Hammour, Rand Abu; Yassein, Muneer Bani; Al‐Qassas, Raad S.; Torralbo, Juan Alfonso Lara; Lizcano, David
• Other Names: Miranda Breno guestEditor.; Tuya Javier guestEditor.; Garrido Alejandra guestEditor.
• Is Part Of: Journal of software. Volume 34:Issue 11(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-08-08
• Subjects: cyber security -- forecasting model -- machine learning -- security software testing; Software engineering -- Periodicals; Computer software -- Development -- Periodicals; Software maintenance -- Periodicals; 005.1
• DOI: 10.1002/smr.2489
• Languages: English
• ISSNs: 2047-7473

Abstract

Abstract: As the number of cyber‐attacks on financial institutions has increased over the past few years, an advanced system that is capable of predicting the target of an attack is essential. Such a system needs to be integrated into the existing detection systems of financial institutions as it provides them with proactive controls with which to halt an attack by predicting patterns. Advanced prediction systems also enhance the software design and security testing of new advanced cyber‐security measures by providing new testing scenarios supported by attack forecasting. This present study developed a model that forecasts future network‐based cyber‐attacks on financial institutions using a deep neural network. The dataset that was used to train and test the model consisted of some of the biggest cyber‐attacks on banking institutions over the past three years. This provided insight into new patterns that may end with a cyber‐crime. These new attacks were also evaluated to determine behavioral similarities with the nearest known attack or a combination of several existing attacks. The performance of the forecasting model was then evaluated in a real banking environment and provided a forecasting accuracy of 90.36%. As such, financial institutions can use the proposed forecasting model to improve their security testing measures. Abstract :