BotDetector: An extreme learning machine‐based Internet of Things botnet detection model

Xudong, Dong; Dong, Chen; Chen, Zhenyi; Cheng, Yafang; Chen, Bo

doi:10.1002/ett.3999

Cited by 11 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although AI chips usually have special hardware accelerators, their design also pays attention to flexibility and programmability. This means that AI chips can adapt to different AI tasks and be used flexibly in different application scenarios [9]. The programmable design enables the chip to adapt to the new algorithm and model structure through firmware or software update.…”

Section: Analysis Of Hardware Characteristics Of Ai Chipmentioning

confidence: 99%

Hardware Accelerated Optimization of Deep Learning Model on Artificial Intelligence Chip

Chen

2023

FCIS

View full text Add to dashboard Cite

With the rapid development of deep learning technology, the demand for computing resources is increasing, and the accelerated optimization of hardware on artificial intelligence (AI) chip has become one of the key ways to solve this challenge. This paper aims to explore the hardware acceleration optimization strategy of deep learning model on AI chip to improve the training and inference performance of the model. In this paper, the method and practice of optimizing deep learning model on AI chip are deeply analyzed by comprehensively considering the hardware characteristics such as parallel processing ability, energy-efficient computing, neural network accelerator, flexibility and programmability, high integration and heterogeneous computing structure. By designing and implementing an efficient convolution accelerator, the computational efficiency of the model is improved. The introduction of energy-efficient computing effectively reduces energy consumption, which provides feasibility for the practical application of mobile devices and embedded systems. At the same time, the optimization design of neural network accelerator becomes the core of hardware acceleration, and deep learning calculation such as convolution and matrix operation are accelerated through special hardware structure, which provides strong support for the real-time performance of the model. By analyzing the actual application cases of hardware accelerated optimization in different application scenarios, this paper highlights the key role of hardware accelerated optimization in improving the performance of deep learning model. Hardware accelerated optimization not only improves the computing efficiency, but also provides efficient and intelligent computing support for AI applications in different fields.

show abstract

Section: Analysis Of Hardware Characteristics Of Ai Chipmentioning

confidence: 99%

Hardware Accelerated Optimization of Deep Learning Model on Artificial Intelligence Chip

Chen

2023

FCIS

View full text Add to dashboard Cite

show abstract

“…Some basic features are used in this research, as in [6,19]. The remaining 𝑓𝑐 can be developed into new ones through the engineering feature using onehot encoding [25]. For example, the 𝐷𝑖𝑟 , can be explored into features of 𝐷𝑖𝑟_ <-, 𝐷𝑖𝑟_ <, 𝐷𝑖𝑟_ <-, 𝐷𝑖𝑟_ <->.…”

Section: Feature Engineeringmentioning

confidence: 99%

Analysis of Botnet Attack Communication Pattern Behavior on Computer Networks

2022

IJIES

View full text Add to dashboard Cite

Botnets are a severe threat to a computer network, affecting various aspects of security systems, including spreading malicious programs, phishing, sending spam messages, and click fraud. Because of their negative consequences, botnets must be identified early. Nevertheless, their different characteristics have made them challenging to detect. This research proposes a bot patterns communication detection from traffic flows analysis consisting of three main activities: bot detection, extraction, and communication behavior analysis phases. This proposed model aims to obtain a specific behavior of bot attacks, which can be used as an early warning bots attack system. The process of bot patterns communication detection depends on the accuracy of bot detection, so the model improves the pre-processing phase and uses multi-model classification. Improvement in the pre-processing phase is carried out in the feature engineering section using the concept of one-hot encoding. Several machine learning classification models are used to obtain the best detection accuracy: Decision tree, Random forest, Logistic regression, k-NN, and Naïve Bayes. Furthermore, the model has been tested on two different datasets, namely the NCC and CTU-13. The experimental results show that the proposed model is optimal and recognizes bot activities well. The accuracy detection is obtained at 99.99%. Besides, the model can also identify the bot's attack activity scenario and communication behavior in three types: centralized, distributed, and spread.

show abstract

“…Today, most distributed denial-of-service (DDoS) attacks are initiated by botnets, and this case is slowly turning to IoT systems as well. 7 Decision support systems with an artificial intelligence infrastructure are systems that can do much more than humans. There are many studies in the literature where IoT technologies and artificial intelligence approaches are used together.…”

Section: Introductionmentioning

confidence: 99%

“…The dataset they used for their studies was freely available and their overall accuracy in detecting DDoS attacks was 99.38%. Dong et al 7 designed a machine learning-based detector for botnet detection. In their proposed approach, they performed analysis using extreme learning machine (ELM) method instead of deep learning models.…”

Section: Introductionmentioning

confidence: 99%

Detecting attacks on IoT devices with probabilistic Bayesian neural networks and hunger games search optimization approaches

Toğaçar

2021

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Technologies that enable physical objects to communicate with each other are attracting a lot of interest day by day. Internet of Things (IoT) is a communication network that is used to connect with technological devices and systems.The growth of IoT networks has led to malicious targeting of these systems by third parties. To prevent such malicious purposes, network security should be at the forefront. Recently, artificial intelligence-based approaches have been used in security domains. Two accessible datasets were used in this study. The datasets consist of simulated bot IoT network traffic data containing distributed denial-of-service (DDoS) attack types. In the proposed approach, probabilistic Bayesian neural networks and normal Bayesian neural networks are used as the deep learning models. All features of the dataset were trained using two models. Then, the datasets were optimized using hunger games search (HGS) method and the most efficient parameters of the datasets were selected and retrained using deep learning models. In the analysis performed using the proposed approach, an overall accuracy of 100% was obtained for the dataset used in the first experiment and 99.99% for the dataset used in the second experiment. It was also observed that metaheuristic optimization helps the proposed approach to save time in detecting DDoS attacks.

show abstract

BotDetector: An extreme learning machine‐based Internet of Things botnet detection model

Cited by 11 publications

References 39 publications

Hardware Accelerated Optimization of Deep Learning Model on Artificial Intelligence Chip

Hardware Accelerated Optimization of Deep Learning Model on Artificial Intelligence Chip

Analysis of Botnet Attack Communication Pattern Behavior on Computer Networks

Detecting attacks on IoT devices with probabilistic Bayesian neural networks and hunger games search optimization approaches

Contact Info

Product

Resources

About