IoT Multi-Vector Cyberattack Detection Based on Machine Learning Algorithms: Traffic Features Analysis, Experiments, and Efficiency

Abstract

Cybersecurity is a common Internet of Things security challenge. The lack of security in IoT devices has led to a great number of devices being compromised, with threats from both inside and outside the IoT infrastructure. Attacks on the IoT infrastructure result in device hacking, data theft, financial loss, instability, or even physical damage to devices. This requires the development of new approaches to ensure high-security levels in IoT infrastructure. To solve this problem, we propose a new approach for IoT cyberattack detection based on machine learning algorithms. The core of the method involves network traffic analyses that IoT devices generate during communication. The proposed approach deals with the set of network traffic features that may indicate the presence of cyberattacks in the IoT infrastructure and compromised IoT devices. Based on the obtained features for each IoT device, the feature vectors are formed. To conclude the possible attack presence, machine learning algorithms were employed. We assessed the complexity and time of machine learning algorithm implementation considering multi-vector cyberattacks on IoT infrastructure. Experiments were conducted to approve the method’s efficiency. The results demonstrated that the network traffic feature-based approach allows the detection of multi-vector cyberattacks with high efficiency.

Machine Learning Techniques for Cyberattack Prevention in IoT Systems: A Comparative Perspective of Cybersecurity and Cyberdefense in Colombia

“…In this case (Figure 13), Y involves the aggregation of weighted inputs (Zi) to generate a prediction. The perceptron, a foundational element within neural networks [21], employs weights ( f ) applied to input features (W) and computes their sum, e.g., as in Figures 2-4 and Tables 2 and 3, oriented with behavioral data [19,63] that are multivector factors of cyberattacks. In addition to precision of calculation assigned to these perceptron analyses, many more inputs are required to facilitate the orientation through the sum of TTPs and attack patterns.…”

“…According to Ref. [63], with a differential schema-oriented perspective model, the purpose is related to analyze the traffic obtained from internal sources (CPS or CSB) about anomaly behavior (feature extraction); this separation has bad or good traffic-related, e.g., DDoS, attacks, in general, MIRAI Botnet. This is achieved (Table 2) through the application of sophisticated techniques, such as those outlined in the MITRE ATT&CK framework [16].…”

Practical Applications to Prevent Cyberattacks on Internet on Battlefield Things (IoBT)

“…The assumption that every device has independent placement has the various other devices placed independently with a combined network representation as PPP within intensity λm classified by the Φm with a consequent˄= ∑_(m=1)^M▒λm. The traditional communication infrastructure lacks within this advanced network, limiting the base communications to D2D [20]. Therefore, device Tm of the m type has the capability of communicating with device yn of the n-type on the condition ‖X_m-y_n ‖≤r_m.…”

Machine Learning Based Cybersecurity Threat Detection for Secure IoT Assisted Cloud Environment

“…Owing to the pervasive nature of such gadgets and due to the simplicity of observing and controlling gadgets from distant places, there occurs a fast advancement in framing various new applications in numerous fields like connected industrial and manufacturing sensors and equipment, smart home devices, health monitoring gadgets, energy management gadgets, wearable devices, etc. [2,3]. The main concern in the IoT network was managing the device's security and data protection from assaults.…”