Analyzing and predicting complex network attack strategies require an efficient way to produce realistic and up-to-date data representing a variety of attack behaviors on diverse network configurations. This work develops a simulation system that fuses four context models: the networks, the system vulnerabilities, the attack behaviors, and the attack scenarios, so as to synthesize multistage attack sequences. The separation of different context models enables flexibility and usability in defining these models, as well as a comprehensive synthesis of attack sequences under different combinations of situations. After describing the design of the context models, an example use of the simulator and sample outputs, including the ground truth actions and sensor observables, will be discussed.
Ideal cyber threat intelligence (CTI) includes insights into attacker strategies that are specific to a network under observation. Such CTI currently requires extensive expert input for obtaining, assessing, and correlating system vulnerabilities into a graphical representation, often referred to as an attack graph (AG). Instead of deriving AGs based on system vulnerabilities, this work advocates the direct use of intrusion alerts. We propose SAGE, an explainable sequence learning pipeline that automatically constructs AGs from intrusion alerts without a priori expert knowledge. SAGE exploits the temporal and probabilistic dependence between alerts in a suffix-based probabilistic deterministic finite automaton (S-PDFA) -a model that brings infrequent severe alerts into the spotlight and summarizes paths leading to them. Attack graphs are extracted from the model on a per-victim, per-objective basis. SAGE is thoroughly evaluated on three open-source intrusion alert datasets collected through security testing competitions in order to analyze distributed multi-stage attacks. SAGE compresses over 330k alerts into 93 AGs that show how specific attacks transpired. The AGs are succinct, interpretable, and provide directly relevant insights into strategic differences and fingerprintable paths. They even show that attackers tend to follow shorter paths after they have discovered a longer one in 84.5% of the cases.
Existing research on cyber threat assessment focuses on analyzing the network vulnerabilities and producing possible attack graphs. Cyber attacks in real-world enterprise networks, however, vary significantly due to not only network and system configurations, but also the attacker’s strategies. This work proposes a cyber-based attacker behavior model (ABM) in conjunction with the Cyber Attack Scenario and Network Defense Simulator to model the interaction between the network and the attackers. The ABM leverages a knowledge-based design and factors in the capability, opportunity, intent, preference, and Cyber Attack Kill Chain integration to model various types of attackers. By varying the types of attackers and the network configurations, and simulating their interactions, we present a method to measure the overall network security against cyber attackers under different scenarios. Simulation results based on four attacker types on two network configurations are shown to demonstrate how different attacker behaviors may lead to different ways to penetrate a network, and how a single misconfiguration may impact network security.
Many cyber attack actions can be observed, but the observables often exhibit intricate feature dependencies, non-homogeneity, and potentially rare yet critical samples. This work tests the ability to learn, model, and synthesize cyber intrusion alerts through Generative Adversarial Networks (GANs), which explore the feature space by reconciling between randomly generated samples and data that reflect a mixture of diverse attack behaviors without a priori knowledge. Through a comprehensive analysis using Jensen-Shannon Divergence, Conditional and Joint Entropy, and mode drops and additions, we show that the Wasserstein-GAN with Gradient Penalty and Mutual Information is more effective in learning to generate realistic alerts than models without Mutual Information constraints. We further show that the added Mutual Information constraint pushes the model to explore the feature space more thoroughly and increases the generation of low probability, yet critical, alert features. This research demonstrates the novel and promising application of unsupervised GANs to learn from limited yet diverse intrusion alerts to generate synthetic alerts that emulate critical dependencies, opening the door to proactive, data-driven cyber threat analyses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.