LiMNet: Early-Stage Detection of IoT Botnets with Lightweight Memory Networks

Giaretta, Lodovico; Lekssays, Ahmed; Carminati, Barbara; Ferrari, Elena; Girdzijauskas, Šarūnas

doi:10.1007/978-3-030-88418-5_29

Cited by 5 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MLTs were used to categorize benign and malicious behaviors, employing a combination of Decision Trees (DTs), K Nearest Neighbors (KNNs), Random Forests (RFs), and Support Vector Machines (SVMs) for processing tasks [18]. Deep Learning Techniques such as FastGRNN, LSTMs, and GRU were evaluated by Giaretta et al [19], focusing on the identification of infected and compromised devices. Machine Learning Techniques were devised to detect IoT devices affected by botnets [20].…”

Section: Review Of Literaturementioning

confidence: 99%

Deep Learning-Based Detection of IoT Botnet Attacks: An Exploration of Residual Networks

Govindaraji,

Periyasamy,

Vidyaathulasiraman

2023

IJSSE

View full text Add to dashboard Cite

Modern enterprises increasingly employ Internet of Things (IoT) devices across various sectors to enhance service provision, with applications spanning from healthcare to academia. However, the widespread adoption of IoT technology introduces significant security vulnerabilities. Particularly, these devices are susceptible to cyber-attacks, notably those orchestrated by botnets. The challenge of addressing this security issue is further compounded by the devices' memory and energy constraints, which limit the implementation of robust security measures. The present study introduces a Deep Learning Techniques (DLT) based approach, termed Detection of Intrusions in IoT using Residual Networks (DIIOTRNs), to preemptively identify IoT botnet attacks. These attacks typically undergo several stages prior to execution, providing an opportunity for early detection. The proposed DIIOTRNs framework integrates Convolution Neural Networks (CNNs) and Long Short-Term Memories (LSTMs) to effectively detect potential threats. The framework was subjected to empirical testing and demonstrated promising results, achieving accuracy levels exceeding 90%. Thus, the DIIOTRNs approach offers a promising solution to the pressing issue of IoT security, particularly in the context of botnet attacks. Further research is warranted to refine and optimize this framework for broad adoption across the IoT landscape.

show abstract

Section: Review Of Literaturementioning

confidence: 99%

Deep Learning-Based Detection of IoT Botnet Attacks: An Exploration of Residual Networks

Govindaraji,

Periyasamy,

Vidyaathulasiraman

2023

IJSSE

View full text Add to dashboard Cite

show abstract

“…On the other hand, they conducted the same experiment using multilayer perceptron (MLPN) and long short-term memory (LSTM) and achieved accuracies of 89.1 and 87.6, respectively. In [ 25 ], the authors examined and compared three recurrent deep learning algorithms: FastGRNN, LSTM, and GRU. They used the three models to identify infected and soon-to-be-infected devices.…”

Section: Literature Reviewmentioning

confidence: 99%

Cross Deep Learning Method for Effectively Detecting the Propagation of IoT Botnet

Wazzan

Alghazzawi

Albeshri

et al. 2022

Sensors

View full text Add to dashboard Cite

In recent times, organisations in a variety of businesses, such as healthcare, education, and others, have been using the Internet of Things (IoT) to produce more competent and improved services. The widespread use of IoT devices makes our lives easier. On the other hand, the IoT devices that we use suffer vulnerabilities that may impact our lives. These unsafe devices accelerate and ease cybersecurity attacks, specifically when using a botnet. Moreover, restrictions on IoT device resources, such as limitations in power consumption and the central processing unit and memory, intensify this issue because they limit the security techniques that can be used to protect IoT devices. Fortunately, botnets go through different stages before they can start attacks, and they can be detected in the early stage. This research paper proposes a framework focusing on detecting an IoT botnet in the early stage. An empirical experiment was conducted to investigate the behaviour of the early stage of the botnet, and then a baseline machine learning model was implemented for early detection. Furthermore, the authors developed an effective detection method, namely, Cross CNN_LSTM, to detect the IoT botnet based on using fusion deep learning models of a convolutional neural network (CNN) and long short-term memory (LSTM). According to the conducted experiments, the results show that the suggested model is accurate and outperforms some of the state-of-the-art methods, and it achieves 99.7 accuracy. Finally, the authors developed a kill chain model to prevent IoT botnet attacks in the early stage.

show abstract