Predicting the Effects of DDoS Attacks on a Network of Critical Infrastructures

Abstract

Abstract-Over the last decade, the level of critical infrastructure technology has been steadily transforming in order to keep pace with the growing demand for the services offered. The implementation of the smart grid, which relies on a complex and intelligent level of interconnectivity, is one example of how vital amenity provision is being refined. However, with this change, the risk of threats from the digital domain must be calculated. Superior interconnectivity between infrastructures means that the future cascading impacts of successful cyberattacks are unknown. One such threat being faced in the digital domain is the Distributed Denial of Service (DDoS) attack. A DDoS has the goal of incapacitating a server, network or service, by barraging a target with external data traffic in the form of communication requests. DDoS have the potential to cause a critical infrastructure outage, and the subsequent impact on a network of such infrastructures is yet unknown. In this paper, an approach for assessing the future impacts of a cyber-attack in a network of critical infrastructures is presented; with a focus on DDoS attacks. A simulation of a critical infrastructure network provides data to represent both normal run-time and an attack scenario. Using this dataset, a technique for assessing the future impact of disruptions on integrated critical infrastructure network, is demonstrated.

Analisis Statistik Log Jaringan Untuk Deteksi Serangan Ddos Berbasis Neural Network

“…DDoS disebut sebagai senjata pilihan hacker karena telah terbukti menjadi ancaman permanen bagi pengguna, organisasi dan infrastruktur di Internet. Di sisi lain, serangan jaringan merupakan risiko untuk integritas, kerahasiaan dan ketersediaan sumber daya yang disediakan oleh organisasi [2].…”

“…. 2. Bagaimana performa deteksi serangan DDoS yang didasarkan pada analisis statistik terhadap log aktivitas jaringan menggunakan metode neural network sebagai fungsi deteksi berdasarkan data pelatihan dan pengujian.…”

Machine Learning-Based Distributed Denial of Services (DDoS) Attack Detection in Intelligent Information Systems

“…Abhishta et al(Abhishta et al, 2017) analyzes the impact of DDoS attack announcements on victim stock prices and finds a significant negative impact in cases where the attack creates an interruption in services. Hurst et al(Hurst et al, 2015) focuses on predicting the effects of DDoS attacks on a network of critical infrastructures and demonstrates a technique for assessing the future impact of disruptions on an integrated critical infrastructure network. Overall, the papers suggest that the consequences of a DDoS attack can be significant and wide-ranging, affecting not only the target but also other stakeholders and potentially causing financial losses.…”

Multischeme feedforward artificial neural network architecture for DDoS attack detection

“…In general, packet flow patterns from DDoS attacks behave like normal packet data flow, making it difficult for network administrators to distinguish between proper data packet flow and attack data packet flow [4]. DDoS attacks for a long time can cause the server system to lose all of its services [5,6]. Detection of the packet flow is one of the techniques to prevent DDoS attacks.…”