Applications of artificial immune systems to computer security: A survey

Fernandes, Diogo A. B.; Freire, Mrio M.; Fazendeiro, Paulo; Incio, Pedro R.M.

doi:10.1016/j.jisa.2017.06.007

Cited by 40 publications

(29 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, in a similar way as GAs are inspired by organic evolution (i.e., Darwinian evolution), the artificial immune system (AIS) algorithms [5][6][7][8][9][10] are inspired by the immune system of vertebrates. These algorithms share some of the characteristics of the GAs, and they are currently used for solving practical problems [11,12].…”

Section: Introductionmentioning

confidence: 99%

An Evolutionary Computing Model for the Study of Within-Host Evolution

Gómez-Mompeán

Lahoz-Beltrá

2020

Computation

View full text Add to dashboard Cite

Evolution of an individual within another individual is known as within-host dynamics (WHD). The most common modeling technique to study WHD involves ordinary differential equations (ODEs). In the field of biology, models of this kind assume, for example, that both the number of viruses and the number of mouse cells susceptible to being infected change according to their interaction as stated in the ODE model. However, viruses can undergo mutations and, consequently, evolve inside the mouse, whereas the mouse, in turn, displays evolutionary mechanisms through its immune system (e.g., clonal selection), defending against the invading virus. In this work, as the main novelty, we propose an evolutionary WHD model simulating the coexistence of an evolving invader within a host. In addition, instead of using ODEs we developed an alternative methodology consisting of the hybridization of a genetic algorithm with an artificial immune system. Aside from the model, interest in biology, and its potential clinical use, the proposed WHD model may be useful in those cases where the invader exhibits evolutionary changes, for instance, in the design of anti-virus software, intrusion detection algorithms in a corporation’s computer systems, etc. The model successfully simulates two intruder detection paradigms (i.e., humoral detection, danger detection) in which the intruder represents an evolving invader or guest (e.g., virus, computer program,) that infects a host (e.g., mouse, computer memory). The obtained results open up the possibility of simulating environments in which two entities (guest versus host) compete evolutionarily with each other when occupying the same space (e.g., organ cells, computer memory, network).

show abstract

Section: Introductionmentioning

confidence: 99%

An Evolutionary Computing Model for the Study of Within-Host Evolution

Gómez-Mompeán

Lahoz-Beltrá

2020

Computation

View full text Add to dashboard Cite

show abstract

“…The reputational and financial damages are just catastrophic for both organizations and governments. A class of security solutions that has attracted researchers over the last twenty years consists of enabling software applications to become immune against attacks [1][2][3][4]. This is a challenging area as it integrates several domains including anomaly-based intrusion detection and prevention [5][6][7][8][9][10][11], application partitioning and sandboxing [12][13][14][15], automatic error detection and patching [3,4], as well as collaborative application communities [1,16,17].…”

Section: Introductionmentioning

confidence: 99%

“…(4) When the behavioral model is learned: before program execution (statically) [11] or during program execution (dynamically) [6,10,18]; and (5) How the model is constructed: finite state automaton [6,10,11,18], or machine learning including supervised [2,19], semi-supervised and unsupervised learning.…”

Section: Introductionmentioning

confidence: 99%

Application-Level Unsupervised Outlier-Based Intrusion Detection and Prevention

Iraqi

Bakkali

2019

Security and Communication Networks

View full text Add to dashboard Cite

As cyber threats are permanently jeopardizing individuals privacy and organizations’ security, there have been several efforts to empower software applications with built-in immunity. In this paper, we present our approach to immune applications through application-level, unsupervised, outlier-based intrusion detection and prevention. Our framework allows tracking application domain objects all along the processing lifecycle. It also leverages the application business context and learns from production data, without creating any training burden on the application owner. Moreover, as our framework uses runtime application instrumentation, it incurs no additional cost on the application provider. We build a fine-grained and rich-feature application behavioral model that gets down to the method level and its invocation context. We define features to be independent from the variable structure of method invocation parameters and returned values, while preserving security-relevant information. We implemented our framework in a Java environment and evaluated it on a widely-used, enterprise-grade, and open-source ERP. We tested several unsupervised outlier detection algorithms and distance functions. Our framework achieved the best results in terms of effectiveness using the Local Outlier Factor algorithm and the Clark distance, while the average instrumentation overhead per intercepted call remains acceptable.

show abstract

“…The immune system is responsible for guarding the human body against the foreign and dangerous microorganisms called pathogens. To overcome these pathogens, the immune system depends on innate and adaptive immune subsystems [3]. The innate immune subsystem is considered the immutable first line of defense for alarming danger signals around suspicious item.…”

Section: Introductionmentioning

confidence: 99%

An Immunity-based Error Containment Algorithm for Database Intrusion Response Systems

Yanes¹,

Mostafa²,

Alshammari³

et al. 2019

IJACSA

View full text Add to dashboard Cite

The immune system has received a special attention as a potential source of inspiration for innovative approaches to solve database security issues and build artificial immune systems. Database security issues need to be correctly identified to ensure that suitable responses are taken. This paper proposes an immunity-based error containment algorithm for providing optimum response in detected intrusions. The objective of the proposed algorithm is to reduce the false positive alarms to the minimum since not all the incidents are malicious in nature. The proposed algorithm is based on apoptotic and necrotic signals which are parts of the immunity structure in human immune system. Apoptotic signals define low-level alerts that could result from legitimate users but could be also the prerequisites for an attack, while necrotic signals define highlevel alerts that result from actual successful attacks.

show abstract

Applications of artificial immune systems to computer security: A survey

Cited by 40 publications

References 37 publications

An Evolutionary Computing Model for the Study of Within-Host Evolution

An Evolutionary Computing Model for the Study of Within-Host Evolution

Application-Level Unsupervised Outlier-Based Intrusion Detection and Prevention

An Immunity-based Error Containment Algorithm for Database Intrusion Response Systems

Contact Info

Product

Resources

About