A DDoS Detection Method for Socially Aware Networking Based on Forecasting Fusion Feature Sequence

Cheng, Jieren; Zhou, Jinghe; Liu, Qiang; Tang, Xiangyan; Guo, Yanxiang

doi:10.1093/comjnl/bxy025

Cited by 19 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In simple terms, remote sensing image feature discretization is to adopt a specific method to divide a continuous feature interval on the image into a limited number of cells, then to associate these cells with a set of discrete values. The discretization of continuous features (also called continuous attributes) is an important preprocessing step for data mining and machine learning, and is directly related to the effect of mining or learning [6,19].…”

Section: Remote Sensing Image Feature Discretizationmentioning

confidence: 99%

A multivariable optical remote sensing image feature discretization method applied to marine vessel targets recognition

Huang

Chen

Wang

2019

Multimed Tools Appl

View full text Add to dashboard Cite

The effective extraction of continuous features in ocean optical remote sensing image is the key to achieve the automatic detection and identification for marine vessel targets. Since many of the existing data mining algorithms can only deal with discrete attributes, it is necessary to transform the continuous features into discrete ones for adapting to these intelligent algorithms. However, most of the current discretization methods do not consider the mutual exclusion within the attribute set when selecting breakpoints, and cannot guarantee that the indiscernible relationship of information system is not destroyed. Obviously, they are not suitable for processing ocean optical remote sensing data with multiple features. Aiming at this problem, a multivariable optical remote sensing image feature discretization method applied to marine vessel targets recognition is presented in this paper. Firstly, the information equivalent model of remote sensing image is established based on the theories of information entropy and rough set. Secondly, the change extent of indiscernible relationship in the model before and after discretization is evaluated. Thirdly, multiple scans are executed for each band until the termination condition is satisfied for generating the optimal number of intervals. Finally, we carry out the simulation analysis of the high-resolution remote sensing image data collected near the coast of South China Sea. In addition, we also compare the proposed method with the current mainstream discretization algorithms. Experiments validate that the proposed method has better comprehensive performance in terms of interval number, data consistency, running time, prediction accuracy and recognition rate.

show abstract

Section: Remote Sensing Image Feature Discretizationmentioning

confidence: 99%

A multivariable optical remote sensing image feature discretization method applied to marine vessel targets recognition

Huang

Chen

Wang

2019

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Moreover, the idea of provided attack detection is vaguely presented. There are more investigations that are dedicated to the specific type of the attacks [27], [28]. Bhattacharya and Selvakumar [27] suggested a multi-measure multi-weight ranking approach for the identification of the network features for the detection of denial of service (DoS) and probe attacks.…”

Section: Review Of Related Workmentioning

confidence: 99%

“…The approach combines the filter and wrapper feature selection methods and clustering methods to assign multiple weights to each feature. Cheng et al [28] proposed a DDoS detection method for socially aware networking based on the time-series autoregressive integrated moving average model. The model describes a multi-protocol-fusion feature to characterize normal network flows.…”

Section: Review Of Related Workmentioning

confidence: 99%

Logical filter approach for early stage cyber-attack detection

et al. 2019

View full text Add to dashboard Cite

The planned in advance cyber-attacks cause the most damage for the users of the information systems. Such attacks can take a very long time, require considerable financial and human resources, and therefore, they can only be organized by large interest groups. Furthermore, current intrusion detection systems, intrusion prevention systems and intrusion response systems used to protect against cyber-attacks have several shortcomings. Such systems respond only to the attack itself when it is too late to take a preventive action and they are not suitable for detecting an attack in early stages when it is possible to block the attack and minimize the losses. Early detection requires detailed monitoring of network and system parameters to be able to accurately identify the early stages of the attack when it is still possible to kill the attack chain. In this paper, we propose to consider an attack chain consisting of nine stages. The method to detect early stage cyberattack based on the attack chain analysis using hardware implementation of logical filters is suggested. The performed experiment acknowledges the possibility to detect the attack in the early stages.

show abstract

“…Only unsigned integer types are accepted. • NOTIFY: if an email is specified, an error is thrown if the address does not comply with the email Internet Message Format RFC2822 Standard [23], using the validators of the Apache Commons project 8 . The existence of the email domain is also checked, although only a warning is reported if not found for the same reasons we did with IPs or DNS names.…”

Section: 941 * Errors Found When Checking Specified Abstract In Outmentioning

confidence: 99%

“…They may be performed over private companies, public institutions, or military infrastructures [4]. Consequences may be varied: steal user information [5], alter the normal behavior of services [6][7][8], data hijacking [9], or taking control of an infrastructure to perform malicious activities [10]. Both web applications and their hosting servers are very common attack targets [11].…”

Section: Introductionmentioning

confidence: 99%

Towards Improving Productivity in NMapSecurity Audits

Redondo

Cuesta

2019

JWE

View full text Add to dashboard Cite

Maintaining an adequate security level in computer infrastructures, like Internet-facing web servers, requires periodic assessment of their vulnerabilities with specialized security tools. nmap is arguably the most popular one, due to its versatility, powerful features, and low resource usage. However, this versatility can turn its usage difficult and error-prone, as it implements a lot of features and reports errors at runtime. This can lead to suboptimal results while designing auditing tasks. This research aims to decrease this complexity by developing a web GUI that favors experimentation, on-demand scans, and provides solutions to several shortcomings detected in the official one. We complemented it with a Domain Specific Language that implements early detection and reporting of syntax, type, and semantic errors when creating audit tasks. Both expand nmap possibilities, creating robust, schedulable, distributable, and portable auditing tasks able to find anomalies analyzing their output. Our initial release shows that the web GUI has been well received by several security related media and professionals. The language can detect and report a wide range of potential errors, substantially increasing the robustness of the created tasks. Therefore,

show abstract

A DDoS Detection Method for Socially Aware Networking Based on Forecasting Fusion Feature Sequence

Cited by 19 publications

References 27 publications

A multivariable optical remote sensing image feature discretization method applied to marine vessel targets recognition

A multivariable optical remote sensing image feature discretization method applied to marine vessel targets recognition

Logical filter approach for early stage cyber-attack detection

Towards Improving Productivity in NMapSecurity Audits

Contact Info

Product

Resources

About