A Divergence-measure Based Classification Method for Detecting Anomalies in Network Traffic

Balagani, Kiran S.; Phoha, Vir V.; Kuchimanchi, G.K.

doi:10.1109/icnsc.2007.372808

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By identifying their examples throughout the learning phase, machine learning can obtain high efficiency in traffic classification using Bayesian Neural Networks with or without input from the application. Balagani et al [24] used the kmeans method for unlabeled data to increase classification precision for outlier detection. Additionally, a classifier that learns incrementally is the best choice for acquiring the necessary information for continuous or flow data.…”

Section: Background To the Malware Detection Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Malware Cyber Threat Intelligence System for Internet of Things (IoT) Using Machine Learning

Xiao

2023

JCSANDM

View full text Add to dashboard Cite

Cyber Intelligence (CI) is a sophisticated security solution that uses machine learning models to protect networks against cyber-attack. Security concerns to IoT devices are exacerbated because of their inherent weaknesses in memory systems, physical and online interfaces, and network services. IoT devices are vulnerable to attacks because of the communication channels. That raises the risk of spoofing and Denial-of-Service (DoS) attacks on the entire system, which is a severe problem. Since the IoT ecosystem does not have encryption and access restrictions, cloud-based communications and data storage have become increasingly popular. An IoT-based Cyber Threat Intelligence System (IoT-CTIS) is designed in this article to detect malware and security threads using a machine learning algorithm. Because hackers are continuously attempting to get their hands on sensitive information, it is important that IoT devices have strong authentication measures in place. Multifactor authentication, digital certificates, and biometrics are just some of the methods that may be used to verify the identity of an Internet of Things device. All devices use Machine Learning (ML) assisted Logistic Regression (LR) techniques to address memory and Internet interface vulnerabilities. System integrity concerns, such as spoofing and Denial of Service (DoS) attacks, must be minimized using the Random Forest (RF) Algorithm. Default passwords are often provided with IoT devices, and many users don’t bother to change them, making it simple for cybercriminals to get access. In other instances, people design insecure passwords that are easy to crack. The results of the experiments show that the method outperforms other similar strategies in terms of identification and wrong alarms. Checking your alarm system’s functionality both locally and in terms of its connection to the monitoring centre is why you do it. Make sure your alarm system is working properly by checking it on a regular basis. It is recommended that you do system tests at least once every three months. The experimental analysis of IoT-CTIS outperforms the method in terms of accuracy (90%), precision (90%), F-measure (88%), Re-call (90%), RMSE (15%), MSE (5%), TPR (89%), TNR (8%), FRP (89%), FNR (8%), Security (93%), MCC (92%).

show abstract

Section: Background To the Malware Detection Modelsmentioning

confidence: 99%

“…The security and MCC of the suggested IoT-CTIS system are higher than the existing models SVM, CNN, DT, LDA, and NB. The security and MCC are expressed in Equations ( 23) and (24).…”

Section: Fpr =mentioning

confidence: 99%