Defending Malicious Script Attacks Using Machine Learning Classifiers

Khan, Nayeem Ahmad; Abdullah, Johari; Khan, Adnan Shahid

doi:10.1155/2017/5360472

Cited by 48 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The creation of a training set may face difficulties. The protection of web applications, for example, should contain all combinations of endpoints devices and cookies due to their high number [ 11 ]. Overcoming such difficulties is crucial for the dataset quality to perform high accuracy classification.…”

Section: Related Workmentioning

confidence: 99%

Study of Machine Learning for Cloud Assisted IoT Security as a Service

Alsharif

Rawat

2021

Sensors

View full text Add to dashboard Cite

Machine learning (ML) has been emerging as a viable solution for intrusion detection systems (IDS) to secure IoT devices against different types of attacks. ML based IDS (ML-IDS) normally detect network traffic anomalies caused by known attacks as well as newly introduced attacks. Recent research focuses on the functionality metrics of ML techniques, depicting their prediction effectiveness, but overlooked their operational requirements. ML techniques are resource-demanding that require careful adaptation to fit the limited computing resources of a large sector of their operational platform, namely, embedded systems. In this paper, we propose cloud-based service architecture for managing ML models that best fit different IoT device operational configurations for security. An IoT device may benefit from such a service by offloading to the cloud heavy-weight activities such as feature selection, model building, training, and validation, thus reducing its IDS maintenance workload at the IoT device and get the security model back from the cloud as a service.

show abstract

Section: Related Workmentioning

confidence: 99%

Study of Machine Learning for Cloud Assisted IoT Security as a Service

Alsharif

Rawat

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Link Guard works by breaking down the contrasts between the visual connection and the real link.it first concentrates the DNS names from the genuine and the visual connection .it at that point looks at the real and visual DNS names, if these names are not the same ,at that point it is phishing of class. Nayeem Khan, Johari Abdullah, Adnan Shahid Khan [9] these author has design methodologies for defending malicious script attacks using machine learning classifies algorithm Naïve Bayes. Security is based on to correlative methodologies, signature based and heuristic based identification approaches.…”

Section: Related Workmentioning

confidence: 99%

A novel approach for phishing emails real time classifica-tion using k-means algorithm

Mhaske-Dhamdhere¹,

Vanjale²

2017

IJET

View full text Add to dashboard Cite

The dangers phishing becomes considerably bigger problem in online networking, for example, Facebook, twitter and Google+. The phishing is normally completed by email mocking or texting and it frequently guides client to enter points of interest at a phony sites whose look and feel are practically indistinguishable to the honest to goodness. Non-technical user resists learning of anti-phishing technic. Also not permanently remember phishing learning. Software solutions such as authentication and security warnings are still depending on end user action. In this paper we are mainly focus on a novel approach of real time phishing email classification using K-means algorithm. For this we uses 160 emails of last year computer engineering students. we get True positive of legitimate and phishing as 67% and 80% and true negative is 30 % and 20%.,which is very high so we ask same users reasons which I mainly categories into three categories ,look and feel of email, email technical parameters, and email structure.

show abstract

“…User's identity and privacy must be always protected especially when performing authentication. The proposed work can be extended to enhance end to end security mechanism in network intrusion detection system or malware detection system (Ahmad et al, 2021;Dildar et al, 2017;Khan et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Biometric Blockchain-based Multifactor Privacy Perserving Authentication Scheme for VANETs

Gumis

Money²,

Affandi³

et al. 2021

JITA

View full text Add to dashboard Cite

To provide the most suitable or compatible scheme to work against various attack toward vehicular ad hoc networks (VANETs) is very challenging. Not only that the high authentication and communication overhead also became a problem for VANETs. Thus, in this paper we use multifactor authentication that could resist various attack toward VANETs. A biometric blockchain-based multifactor privacy-preserving authentication scheme for VANETs. This scheme is proposed by using a new robust pseudo-identity multifactor VANET scheme based on Physical Unclonable Functions (PUF) and biometric data of the vehicle’s authorized user. To calculate the computational cost and the authentication overhead, we compare three of our computational cost and authentication overhead below. From the complexity analysis this proposed scheme has a lower authentication overhead and offers better security level and a low computational cost can be achieved. From the perspective of future, we hope that the cost that involve in this scheme still can be reduce as we offer a high security level. Not only that, but we also hope that this scheme can be implemented practically.

show abstract

Defending Malicious Script Attacks Using Machine Learning Classifiers

Cited by 48 publications

References 18 publications

Study of Machine Learning for Cloud Assisted IoT Security as a Service

Study of Machine Learning for Cloud Assisted IoT Security as a Service

A novel approach for phishing emails real time classifica-tion using k-means algorithm

Biometric Blockchain-based Multifactor Privacy Perserving Authentication Scheme for VANETs

Contact Info

Product

Resources

About