Adaptive intrusion detection via GA-GOGMM-based pattern learning with fuzzy rough set-based attribute selection

Liu, Jin Ping; Zhang, Wuxia; Tang, Zhaohui; Xie, Yongfang; Ma, Tianyu; Zhang, Jingjing; Zhang, Guoyong; Niyoyita, Jean Paul

doi:10.1016/j.eswa.2019.112845

Cited by 40 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, under the background of the fast advancement of the information age, the amount of computer network clients is showing a geometric growth rate [1]. How to effectively ensure the information security of computer networks is particularly important for users.…”

Section: Introductionmentioning

confidence: 99%

Intrusion Detection Method Based on Adaptive Clonal Genetic Algorithm and Backpropagation Neural Network

Liu

Zhou

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

Intrusion Detection System (IDS) is an important part of ensuring network security. When the system faces network attacks, it can identify the source of threats in a timely and accurate manner and adjust strategies to prevent hackers from intruding. Efficient IDS can identify external threats well, but traditional IDS has poor performance and low recognition accuracy. To improve the detection rate and accuracy of IDS, this paper proposes a novel ACGA-BPNN method based on adaptive clonal genetic algorithm (ACGA) and backpropagation neural network (BPNN). ACGA-BPNN is simulated on the KDD-CUP’99 and UNSW-NB15 data sets. The simulation results indicate that, in contrast to the methods based on simulated annealing (SA) and genetic algorithm (GA), the detection rate and accuracy of ACGA-BPNN are much higher than of GA-BPNN and SA-BPNN. In the classification results of KDD-CUP’99, the classification accuracy of ACGA-BPNN is 11% higher than GA-BPNN and 24.2% higher than SA-BPNN, and F-score reaches 99.0%. In addition, ACGA-BPNN has good global searchability and its convergence speed is higher than that of GA-BPNN and SA-BPNN. Furthermore, ACGA-BPNN significantly improves the overall detection performance of IDS.

show abstract

Section: Introductionmentioning

confidence: 99%

Intrusion Detection Method Based on Adaptive Clonal Genetic Algorithm and Backpropagation Neural Network

Liu

Zhou

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…The model can be expanded to a more realistic scenario when the vulnerability graph changes because the attack is discovered or the intrusion detection system of the IoT is trigged. Liu et al [28] proposed an adaptive intrusion detection approach using the fuzzy rough set theory and a new pattern learning. Using a greedy approach, the authors of [28] introduced a Gaussian mixture model clustering method aiming at obtaining the intrinsic structure of instances of computer networks.…”

Section: Literature Review On Ssidmentioning

confidence: 99%

“…Liu et al [28] proposed an adaptive intrusion detection approach using the fuzzy rough set theory and a new pattern learning. Using a greedy approach, the authors of [28] introduced a Gaussian mixture model clustering method aiming at obtaining the intrinsic structure of instances of computer networks.…”

Section: Literature Review On Ssidmentioning

confidence: 99%

A Framework to Test Resistency of Detection Algorithms for Stepping‐Stone Intrusion on Time‐Jittering Manipulation

Wang

Yang

Workman

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Hackers on the Internet usually send attacking packets using compromised hosts, called stepping-stones, in order to avoid being detected and caught. With stepping-stone attacks, an intruder remotely logins these stepping-stones using programs like SSH or telnet, uses a chain of Internet hosts as relay machines, and then sends the attacking packets. A great number of detection approaches have been developed for stepping-stone intrusion (SSI) in the literature. Many of these existing detection methods worked effectively only when session manipulation by intruders is not present. When the session is manipulated by attackers, there are few known effective detection methods for SSI. It is important to know whether a detection algorithm for SSI is resistant on session manipulation by attackers. For session manipulation with chaff perturbation, software tools such as Scapy can be used to inject meaningless packets into a data stream. However, to the best of our knowledge, there are no existing effective tools or efficient algorithms to produce time-jittered network traffic that can be used to test whether an SSI detection method is resistant on intruders’ time-jittering manipulation. In this paper, we propose a framework to test resistency of detection algorithms for SSI on time-jittering manipulation. Our proposed framework can be used to test whether an existing or new SSI detection method is resistant on session manipulation by intruders with time-jittering.

show abstract

“…Since linear models cannot fit the complex nonlinear relations in CIPs, researchers pay more attention to the nonlinear models, such as artificial neural networks (ANN) and support vector machines (SVM) [17]. In addition, fuzzy inference-based soft sensor models and Gaussian process regression (GPR) models [18][19][20][21] are also widely used. For instance, Pani et al [22] proposed a Takagi-Surgeon fuzzy inference model, which is a multimodal approach, combining multiple linear sub-models to describe the global nonlinear behaviors of CIPs, for the online monitoring of cement clinker quality.…”

Section: Introductionmentioning

confidence: 99%

STA-APSNFIS: STA-Optimized Adaptive Pre-Sparse Neuro-Fuzzy Inference System for Online Soft Sensor Modeling

Liu

Jiang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In complex industrial processes (CIPs), due to technical and economic limitations, key performance indicators (KPIs), especially the chemical content-related KPIs, are often difficult to measure in real time, which hinders the propagation of advanced process control technologies. This paper presents a soft sensor-based online KPI inference scheme by a state transition algorithm (STA)-optimized adaptive pre-sparse neuro-fuzzy inference system model, called STA-APSNFIS. It introduces a pre-sparse neural network to the traditional adaptive neuro-fuzzy inference system (ANFIS) model to establish an adaptive pre-sparse neuro-fuzzy inference system (APSNFIS) model to alleviate the adverse effects of data redundancy and noise interference in the detectable process monitoring data, which can effectively reduce the complexity of neuro-fuzzy inference system (NFIS) and speed up its convergence. Successively, to avoid being trapped at a local optimum, the STA-based optimization algorithm is adopted to replace the traditional gradient-based optimization approach to achieve an optimal APSNFIS model. Extensive validation and comparative experiments on nonlinear numeric simulation systems, benchmark Tenessee Eastman (TE) process and a real industrial bauxite flotation process demonstrated that the proposed STA-APSNFIS performed favorably against traditional ANFIS model as well as its variants, e.g., PSO-ANFIS, GA-ANFIS, and some other soft sensor-based KPI inference models.

show abstract

Adaptive intrusion detection via GA-GOGMM-based pattern learning with fuzzy rough set-based attribute selection

Cited by 40 publications

References 41 publications

Intrusion Detection Method Based on Adaptive Clonal Genetic Algorithm and Backpropagation Neural Network

Intrusion Detection Method Based on Adaptive Clonal Genetic Algorithm and Backpropagation Neural Network

A Framework to Test Resistency of Detection Algorithms for Stepping‐Stone Intrusion on Time‐Jittering Manipulation

STA-APSNFIS: STA-Optimized Adaptive Pre-Sparse Neuro-Fuzzy Inference System for Online Soft Sensor Modeling

Contact Info

Product

Resources

About