RETRACTED: Detecting Sybil Attack In Wireless Sensor Networks Using Machine Learning Algorithms

Abstract

In sensitive areas such as battlefields, a Wireless Sensor Network (WSN) is especially in military and civilian applications and it is of utmost importance to develop security in these networks. In various respects, this can improve the quality of life. But to be used for protection reasons in multiple situations such as implementation. There is a high risk of being exposed to multiple viruses and hacking attacks. Unauthorized APs for information protection needs to be detected. Any malicious attacks against these networks, Like Sybil Attack leads to breach of security by enacting as a node that illegitimately declares several false identities at the same time. This misleads valid nodes, and they presume each of those identifiers as actual independent nodes by accident. Thus we proposed a machine learning model to detect Sybil attack in network where rawtraffic data has been collected and is used identify authorized and unauthorized APs in an integrated wired/wireless environment.

Data driven intrusion detection for 6LoWPAN based IoT systems

“…Some of them (Al-Hadhrami & Hussain, 2020;Bhale, Dey, Biswas & Nandi, 2020;Cakir, Toklu & Yalcin, 2020;Cakir & Yalcin, 2021;Mbarek, Ge & Pitner, 2020;Sharma, Elmiligi, Gebali & Verma, 2019;Verma & Ranga, 2020;Yavuz, Ünal & Gül, 2018) use simulation data for developing their models but such data may not be very convenient to develop machine learning models especially in realistic attack scenarios because simulators simulate a certain behavior and the data generated by them may not be very realistic. Some other works (Mounica, Vijayasaraswathi & Vasavi, 2021;Rezvy, Luo, Petridis, Lasebae & Zebin, 2019), on the other hand, use outdated network datasets which consist of generic network attacks. The traffic data that constitute these datasets do not represent IoT traffic characteristics.…”

“…Therefore, they are not also suitable for developing IoT-specific intrusion detection systems and we aim to generate a dataset which consists of the traffic data collected from IoT devices in a real testbed in order to develop our models. (iii) Furthermore, the detection capabilities of the proposed models are restricted in the previous works (Cakir et al, 2020;Cakir & Yalcin, 2021;Ioannou & Vassiliou, 2020;Meidan, Bohadana, Mathov, Mirsky, Shabtai, Breitenbacher & Elovici, 2018;Mounica et al, 2021;Thamilarasu & Chawla, 2019;Yavuz et al, 2018) because they generally propose binary classifiers which classify each attack type against benign traffic separately in the form of anomaly detectors. This requires to develop separate models for different attack types so that such systems do not scale well.…”

Detection of unique delete attack in wireless sensor network using gradient thresholding‐long short‐term memory algorithm

“…They identified through crucial analysis of hidden data knowledge obtained from raw traffic internet data. These data are analyzed using supervised, unsupervised, and reinforcement learning to detect sybil attacks 3 . A Denial‐of‐Service (DoS) attack shuts a machine or network, making it inaccessible to users.…”

“…These data are analyzed using supervised, unsupervised, and reinforcement learning to detect sybil attacks. 3 A Denial-of-Service (DoS) attack shuts a machine or network, making it inaccessible to users. Dos attack is prevented through the Co-FAIS method, which uses Throughput and sleep interval data.…”

Exponentially‐spider monkey optimization based allocation of resource in cloud

“…Therefore, machine learning is devised for optimal resource allocations. 16,17 On the other hand, fewer resources are needed as it minimizes the cost of engaged resources. Thus, the allocation of resources is done using cloud-based software services, which needs to make a tradeoff between QoS and occupied resources cost.…”