Efficient algorithm for intrusion attack classification by analyzing KDD Cup 99

Chandolikar, Neelam; Nandavadekar, Vilas D.

doi:10.1109/wocn.2012.6335546

Cited by 27 publications

(20 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this workvarious attacks like DOS, R2L, U2R Prob and normal packet during capturing packet in real time Network in NIDS mode are obtained [9]. Where HIDS focuses on two attributes like log in log out time and login details.…”

Section: Results Analysismentioning

confidence: 99%

“…So there is a probability that produced result can differ from original results. But propose IDS using knowledge of KDD's 99 data set [8,9,12] in which we have study of all type of normal and abnormal behaviors of packets along with 41 attribute defined in KDD'99 data set, after that we have select 8 attribute (see Table 1) from 41 attribute which play important role during identification of intrusion in captured packets [12]. It is clear from produced results that 8 attributes out of the 41 attributes of the captured packets from network have a significance value higher than zero, and the rest have a significance of zero and hence not selected for the results.…”

Section: Discussionmentioning

confidence: 99%

“…To find intrusion there is used a data base which is known as rule based database. Rule base data base has predefine rules related with intrusions in a packet or log file in this work we have used KDD'99 data set [9] as an analysis of attacks and normal packet.…”

Section: Proposed Methodology 21 Proposed Workmentioning

confidence: 99%

See 2 more Smart Citations

A Real Time Host and Network Mobile Agent based Intrusion Detection System (HNMAIDS)

Dwivedi¹,

Rana²,

Patel³

2015

IJCA

View full text Add to dashboard Cite

Computer security is to detect or prevent the process of collecting information or unauthorized access to computers. Detection is a recognition process which helps us to determine if someone tried to enter our system that have been successful, however, and what can be done. Prevention measures help us to pursue unauthorized users called as intruders from accessing any part of the computer system. Computer is being used for everything from banking and investment, businesses to communicate with others via email or messenger programs. Although It may not consider communications top secret, It probably do not want strangers reading email, using computer to attack or intrusion other systems, sending forged messages or email from computer, or examining personal information stored on our computer (such as financial statements). Intruders (also referred to as attackers, crackers) may not care about our identity. Often, they want to take control of the computer, so you can use it to launch attacks on the computer systems. So, they (attackers) hide the control of our computers from their true lease and launch attacks or intrusions, often against very high-profile computer systems like government or financial systems. This research is the study on computer security using proposed A Real Time Host and Network Mobile Agent based Intrusion Detection System (HNMAIDS) which will enhance efficiency as compare earlier agent based intrusion detection system. An Agent based intrusion detection system is intended to detect suspicious behavior on the network/host through agent, where agent will send an alerts signal to the network administrators and so an administrator can prevent intrusions as well as attacks. Presented results are showing the performance of the proposed HNMAIDS.

show abstract

Section: Results Analysismentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Real Time Host and Network Mobile Agent based Intrusion Detection System (HNMAIDS)

Dwivedi¹,

Rana²,

Patel³

2015

IJCA

View full text Add to dashboard Cite

show abstract

“…This chapter propagandize the comprehensive analysis over diversified detection methodologies [8][9][10] which intricate with the scheming of detection accuracy acquired from Host-based network traffic. As per literature concerned, utilizing the support vector machine from classifier based techniques and optimization algorithm from evolutionary techniques in designing the intrusion detection systems makes the researchers widely impressive to design the diversified setups as neither single nor hybrid approaches.…”

Section: Literature Surveymentioning

confidence: 99%

Improved Detecting Host Based Intrusions Based On Hybrid SVM Using Grey Wolf Optimizer

Sathish¹,

Khader²

2017

IJSIA

View full text Add to dashboard Cite

show abstract

“…Chandolikar and Nandavadekar [10] have evaluated the performance of J48 classification algorithm based on the correctly classified instances, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Root relative squared error and kappa statistics measures. They have applied feature selection on KDD cup data set before evaluating the performance of the algorithm.…”

Section: Related Workmentioning

confidence: 99%

Comparative Analysis of Classification Algorithms on KDD'99 Data Set

Arora¹,

Bhatia²,

Singh³

2016

IJCNIS

View full text Add to dashboard Cite

Abstract-Due to the enormous growth of network based services and the need for secure communications over the network there is an increasing emphasis on improving intrusion detection systems so as to detect the growing network attacks. A lot of data mining techniques have been proposed to detect intrusions in the network. In this paper study of two different classification algorithms has been carried out: Naï ve Bayes and J48. Results obtained after applying these algorithms on 10% of the KDD"99 dataset and on 10% of the filtered KDD"99 dataset are compared and analyzed based on several performance metrics. Comparison between these two algorithms is also done on the basis of the percentage of correctly classified instances of different attack categories present in both the datasets as well as the time they take to build their classification models.Overall J48 is a better classifier compared to Naï ve Bayes on both the datasets but it is slow in building the classification model.

show abstract

Efficient algorithm for intrusion attack classification by analyzing KDD Cup 99

Cited by 27 publications

References 2 publications

A Real Time Host and Network Mobile Agent based Intrusion Detection System (HNMAIDS)

A Real Time Host and Network Mobile Agent based Intrusion Detection System (HNMAIDS)

Improved Detecting Host Based Intrusions Based On Hybrid SVM Using Grey Wolf Optimizer

Comparative Analysis of Classification Algorithms on KDD'99 Data Set

Contact Info

Product

Resources

About