Confederation of FCM clustering, ANN and SVM techniques to implement hybrid NIDS using corrected KDD cup 99 dataset

Chandrasekhar, A. M.; Raghuveer, K.

doi:10.1109/iccsp.2014.6949927

Cited by 27 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The statistical results of the detection rate are shown in Figure 4 according to the year. In table 3, the research scheme of [3], [8], and [9] have high detection rate relatively, but [3] used 30 features and [9] used 35 features. In our scheme, we used only 12 features as the inputs.…”

Section: B Experimental and Results Analysismentioning

confidence: 99%

“…In our scheme, we used only 12 features as the inputs. In addition, we only use a simple BP neural network, but [8] used a multi-level detection model including Fuzzy-C-mean clustering, ANN and SVM. So, the comparison shows that the detection rate for DoS attacks is significantly improved with our scheme.…”

Section: B Experimental and Results Analysismentioning

confidence: 99%

“…However, the two-stage detection method does not fully consider the false detection rate in the first detection phase, so that a large amount of attack traffic is mistaken for legal traffic at this stage. A multi-level detection model has been introduced in [8], which is based on the mechanism of the division of labor. The Fuzzy-C-mean clustering, ANN (artificial neural network) and SVM of the model undertake the role of data partitioning, data training and detection respectively.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Research on Detection and Defense Mechanisms of DoS Attacks Based on BP Neural Network and Game Theory

Gao

Zhang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

DoS (Denial of Service) attacks are becoming one of the most serious security threats to global networks. We analyze the existing DoS detection methods and defense mechanisms in depth. In this paper, BP (back propagation) neural networks and game theory are introduced to design detection methods and defense mechanisms for the DoS attacks. The BP neural network DoS attacks detection model uses KDDCUP99 as the dataset and selects multiple feature vectors from the dataset that can efficiently identify DoS attacks by large-scale training, which improves the accuracy of detecting DoS attacks to 99.977%. Furthermore, we use game theory to perform secondary analysis on DoS attacks that are not recognized by the neural network model, so that the detection rate of Dos attacks increases from 99.97% to 99.998%. Finally, we propose a DoS attacks defense strategy based on game theory. The simulation results show that the proposed detection method and defense strategy are effective for DoS attacks.

show abstract

Section: B Experimental and Results Analysismentioning

confidence: 99%

Section: B Experimental and Results Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Detection and Defense Mechanisms of DoS Attacks Based on BP Neural Network and Game Theory

Gao

Zhang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The model is trained effectively by the time training reaches the 100000 episode mark, and weight updates are ceased. Training is one of the important phase where in the problem of under and over-fitting arises [17]. So, the model has to be trained in such a way that the accuracy should be maximized and at the same time the loss should be minimized.…”

Section: System Implementationmentioning

confidence: 99%

Untitled

2018

IJET

View full text Add to dashboard Cite

A lot of breakthroughs have happened in deep neural networks over a period of time. Traditional gradient-based networks require a lot of data to train and learn. When new data is encountered, the models must inefficiently relearn their parameters to effectively learn the new information without any major interference. Neural Turing Machines (NTMs) which have augmented memory capacities, offer the ability to quickly learn and retrieve new information, and hence can potentially remove the disadvantages of conventional models. Here, we demonstrate the ability of a memory-augmented neural network to rapidly assimilate new data, and use this data to make accurate predictions after only a few samples(One-shot). We also introduce a new method for accessing an external memory that focuses on memory content(content-based addressing), unlike previous methods that additionally use memory location based focusing mechanisms. We have also compared accuracy and learning loss of the MANN (Memory Augmented Neural Networks) with LSTM (Long-Short Term Memory) to show which model is a better choice.

show abstract

“…The proposed solution is to subdivide the activities according to some criterion. For example, Chandrasekhar and Raghuveer [3] employed fuzzy clustering to separate data into homogeneous subsets and learn separate artificial neural networks for each of the subsets for further predictions. The best option for consistency of modeled behaviors is to subdivide activities according to semantically meaningful properties which requires domain and system specific knowledge.…”

Section: Introductionmentioning

confidence: 99%

System Misuse Detection Via Informed Behavior Clustering and Modeling

Adilova

Natious

Chen³

et al. 2019

2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)

View full text Add to dashboard Cite

One of the main tasks of cybersecurity is recognizing malicious interactions with an arbitrary system. Currently, the logging information from each interaction can be collected in almost unrestricted amounts, but identification of attacks requires a lot of effort and time of security experts. We propose an approach for identifying fraud activity through modeling normal behavior in interactions with a system via machine learning methods, in particular LSTM neural networks. In order to enrich the modeling with system specific knowledge, we propose to use an interactive visual interface that allows security experts to identify semantically meaningful clusters of interactions. These clusters incorporate domain knowledge and lead to more precise behavior modeling via informed machine learning. We evaluate the proposed approach on a dataset containing logs of interactions with an administrative interface of login and security server. Our empirical results indicate that the informed modeling is capable of capturing normal behavior, which can then be used to detect abnormal behavior.

show abstract

Confederation of FCM clustering, ANN and SVM techniques to implement hybrid NIDS using corrected KDD cup 99 dataset

Cited by 27 publications

References 8 publications

Research on Detection and Defense Mechanisms of DoS Attacks Based on BP Neural Network and Game Theory

Research on Detection and Defense Mechanisms of DoS Attacks Based on BP Neural Network and Game Theory

Untitled

System Misuse Detection Via Informed Behavior Clustering and Modeling

Contact Info

Product

Resources

About