A survey on performance evaluation of artificial intelligence algorithms for improving IoT security systems

The IPv6 extension header mechanism, a new feature of the IPv6 protocol, enhances flexibility and scalability but introduces numerous security threats like firewall evasion and covert channels. Existing threat detection methods face limitations in detection types, universality, and speed. Hence, an adaptive detection model for IPv6 extension header threats (ADM-DDA6) is proposed. Firstly, standard rule sets are designed for common IPv6 extension headers, successfully detecting 70 types of threats from THC-IPv6 and ExtHdr tools using only 20 rules. Secondly, by parsing IPv6 extension headers, matching rules, establishing transition relationships, and deciding packet threat status based on final states (Normal or Abnormal), complex threats like header disorder and header repetition can be detected. Finally, an adaptive rule matching method is introduced, which dynamically selects rule sets based on IPv6 extension header types, effectively reducing rule matching time. Experimental results show that under different threat magnitudes, ADM-DDA6 is 32% faster than Suricata v6.0.12 and 21.2% faster than Snort v3.1.61.0 in detection speed. Additionally, as the number of threats increases, on commodity hardware, ADM-DDA6 incurs only a 0.7% increase in CPU overhead with no significant memory consumption increase, maintains maximum throughput, and exhibits minor performance changes under low and moderate network load conditions.

show abstract

Pragmatic Study of Botnet Attack Detection In An IoT Environment

Vennapureddy,

Srinivasulu

2024

E3S Web Conf.

View full text Add to dashboard Cite

A comprehensive search for primary research published between 2014 and 2023 was carried across several databases. Studies that describe the application of machine learning (ML) and deep learning techniques for if they was carried out across several databases. Studies that described the application of deep learning (DL) and machine learning (ML) methods for IoT botnet attack detection. Numerous facets of contemporary life have been transformed by the Internet of Things (IoT), including home automation, industrial control systems, healthcare, and transportation. On the other hand, as more devices become connected, security risks have also increased, especially from botnets. IoT Botnet attack detection techniques utilizing ML and DL have been developed in order to reduce these dangers. The best DL and ML techniques for IoT botnet attack detection are identified by a detailed examination of evaluation criteria, and performance measures in this systematic review. Performance metrics from well-known machine learning models are used to illustrate how well these machine learning techniques detect and stop Botnet attacks. When it comes to detecting Botnet assaults, deep learning (DL) and traditional machine learning (ML) methods perform similarly well. Furthermore, traditional machine learning systems still have challenges with real-time monitoring, timely detection and adaptability to novel attack approaches.

show abstract

A survey on performance evaluation of artificial intelligence algorithms for improving IoT security systems

Cited by 6 publications

References 53 publications

Blockchain-enabled federated learning-based privacy preservation framework for secure IoT in precision agriculture

Blockchain-enabled federated learning-based privacy preservation framework for secure IoT in precision agriculture

An adaptive detection model for IPv6 extension header threats based on deterministic decision automaton

Pragmatic Study of Botnet Attack Detection In An IoT Environment

Contact Info

Product

Resources

About