A Collaborative and Adaptive Intrusion Detection Based on SVMs and Decision Trees

Teng, Luyao; Teng, Shaohua; Tang, Feiyi; Zhu, Haibin; Zhang, Wei; Liu, Dongning; Lü, Liang

doi:10.1109/icdmw.2014.147

Cited by 14 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because IDS needs to be updated to adjust to the changing environment, the network's diverse and flexible nature significantly shortens the lifetime of detection models.Depending on unique expenses related to computation, money, and time, distributed, centralized, and hybrid approaches must be used.Because of the aforementioned difficulties, current conventional procedures are unable to attain the necessary high-level accuracy. A more through, detailed, and in-depth understanding of the types of intrusion occurrences is needed to guarantee the effectiveness of intrusion detection systems.Network intrusion detection systems have made extensive use of traditional machine learning techniques, including Bayesian [8][9][10], Support Vector Machines [11][12][13][14][15][16], Decision Trees [17][18][19], Logistic Regression [20][21][22][23], and others. These techniques have produced favorable results.…”

Section: Figure I General Architecture Of Industrial Control Systemmentioning

confidence: 99%

DDANet: Deep DenseAttention Learning-Based for Intrusion Detection in Industrial Control Systems

Sharma,

Sahu,

Bajaj

2024

Preprint

View full text Add to dashboard Cite

Industrial control systems (ICSs) are integrated with communication networks and the Internet of Things (IoT), they become more susceptible to cyberattacks, which can have catastrophic effects. However, the lack of sufficient high-quality attack examples has made it very difficult to withstand cyber threats like large-scale, sophisticated, and heterogeneous ICS. Conventional intrusion detection systems (IDSs), designed primarily to assist IT systems, rely heavily on pre-established models and are mostly trained on particular types of cyberattacks. Furthermore, most intrusion detection systems suffer from low accuracy and high false-positive rates when used because they fail to take into account the imbalanced nature of datasets and feature redundancy. In this article,the Deep DenseAttention Learning Model (DDAnet), a novel and inventive deep learning scheme described in this article, is intended to identify and detect cyber attacks that target industrial control systems. The intrusion activity is regarded as a densenet-based network intrusion detection model with an attention model along with a random forest as a classifier. The DDAnet learning scheme has been extensively tested on a real industrial control system dataset. The results of these experiments reveal the great effectiveness of the scheme in identifying different types of data injection attacks on industrial control systems. Furthermore, the scheme has been found to have superior performance compared to state-of-the-art schemes and existing methodologies. The proposed strategy is a versatile method that can be easily deployed in the current ICS infrastructure with minimal effort.

show abstract

Section: Figure I General Architecture Of Industrial Control Systemmentioning

confidence: 99%

DDANet: Deep DenseAttention Learning-Based for Intrusion Detection in Industrial Control Systems

Sharma,

Sahu,

Bajaj

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The second technique leverages an Intrusion Detection and Prevention System (IDS/IPS) approach, utilizing the Decision Tree machine learning classification algorithm [30]. This method actively monitors the network for any signs of attacks, aiming to detect and mitigate threats in real-time.…”

Section: ░ 8 Conclusionmentioning

confidence: 99%

IoT Security Framework Optimized Evaluation for Smart Grid

Kumar,

Gupta,

Kumar

et al. 2024

IJEER

View full text Add to dashboard Cite

Modern systems' needs may be satisfied by smart grid technologies. Since we frequently struggle to effectively manage security, the smart grid's capacity is frequently underutilized. Despite the fact that a variety of solutions have been offered for securing the smart grid, the problem still exists that no single solution can entirely protect the environment. We provide a protection architecture for the IoT-connected smart grid. The proposed framework to secure IoT devices for the smart grid includes three complementary approaches. By conducting a rigorous comparative analysis of our proposed solution alongside four existing models, we contribute to the ongoing discourse on bolstering the security infrastructure of the smart grid IoT environment. Our optimized evaluation provides valuable insights into the strengths, weaknesses, and unique attributes of each model, offering a comprehensive understanding of their respective applicability and efficacy within the intricate realm of sensor-based applications. Two testing configurations were used to evaluate the Threat Mitigation Framework. It demonstrated superior performance in recognizing attacks like XSS across all testing configurations. In each of the two test sets, we also assessed the device management functions, and we found that they accurately recognized and presented IoT for the smart grid controller.

show abstract

“…Traditional machine learning methods have been widely used in network intrusion detection systems, such as Bayesian [ 2 – 4 ], support vector machines [ 5 – 10 ], decision tree [ 11 – 13 ], logistic regression [ 14 – 16 ], and so on. They all have achieved good results.…”

Section: Introductionmentioning

confidence: 99%

Network Intrusion Detection Technology Based on Convolutional Neural Network and BiGRU

Cao

Song

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To solve the problem of low accuracy and high false-alarm rate of existing intrusion detection models for multiple classifications of intrusion behaviors, a network intrusion detection model incorporating convolutional neural network and bidirectional gated recurrent unit is proposed. To solve the problems of many dimensions of features and imbalance of positive and negative samples in the original traffic data, sampling processing is performed with the help of a hybrid sampling algorithm combining ADASYN and RENN, and feature selection is performed by combining random forest algorithm and Pearson correlation analysis; after that, spatial features are extracted by the convolutional neural network, and further features are extracted by incorporating average pooling and max pooling, and then BiGRU is used to extracts long-distance dependent information features to achieve comprehensive and effective feature learning. Finally, the Softmax function is used for classification. In this paper, the proposed model is evaluated on the UNSW_NB15, NSL-KDD, and CIC-IDS2017 data sets with an accuracy of 85.55%, 99.81%, and 99.70%, which is 1.25%, 0.59%, and 0.27% better than the same type model of CNN-GRU.

show abstract

A Collaborative and Adaptive Intrusion Detection Based on SVMs and Decision Trees

Cited by 14 publications

References 15 publications

DDANet: Deep DenseAttention Learning-Based for Intrusion Detection in Industrial Control Systems

DDANet: Deep DenseAttention Learning-Based for Intrusion Detection in Industrial Control Systems

IoT Security Framework Optimized Evaluation for Smart Grid

Network Intrusion Detection Technology Based on Convolutional Neural Network and BiGRU

Contact Info

Product

Resources

About