Fuzzy zero day exploits detector system

Shaout, Adnan; Smyth, Cameron

doi:10.19101/ijacr.2017.730022

Cited by 5 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining the parameter-seeking ability of ant colony optimization algorithm and the nonlinear operation ability of SVM improves the classification performance of SVM; the better global search ability of genetic algorithm is used for the selection of optimal features and the calculation of optimal parameters of SVM, which can avoid the premature sieving of beneficial information in feature selection and further improve the performance of prediction models [8]. It inputs software defect features and historical defect data into the artificial neural network model, compares the error between the output results and the actual results, and corrects the data using a back-propagation algorithm to adjust parameters such as the connection weights of ANNs by an iterative method to continuously optimize and obtain the optimal network parameters [9]. is method has the feature of high prediction accuracy, but the training speed is slow because of the need to iteratively optimize the network parameters.…”

Section: Current Status Of Researchmentioning

confidence: 99%

Deep Learning Software Defect Prediction Methods for Cloud Environments Research

Liu

Wang

2021

Scientific Programming

View full text Add to dashboard Cite

This paper provides an in-depth study and analysis of software defect prediction methods in a cloud environment and uses a deep learning approach to justify software prediction. A cost penalty term is added to the supervised part of the deep ladder network; that is, the misclassification cost of different classes is added to the model. A cost-sensitive deep ladder network-based software defect prediction model is proposed, which effectively mitigates the negative impact of the class imbalance problem on defect prediction. To address the problem of lack or insufficiency of historical data from the same project, a flow learning-based geodesic cross-project software defect prediction method is proposed. Drawing on data information from other projects, a migration learning approach was used to embed the source and target datasets into a Gaussian manifold. The kernel encapsulates the incremental changes between the differences and commonalities between the two domains. To this point, the subspace is the space of two distributional approximations formed by the source and target data transformations, with traditional in-project software defect classifiers used to predict labels. It is found that real-time defect prediction is more practical because it has a smaller amount of code to review; only individual changes need to be reviewed rather than entire files or packages while making it easier for developers to assign fixes to defects. More importantly, this paper combines deep belief network techniques with real-time defect prediction at a fine-grained level and TCA techniques to deal with data imbalance and proposes an improved deep belief network approach for real-time defect prediction, while trying to change the machine learning classifier underlying DBN for different experimental studies, and the results not only validate the effectiveness of using TCA techniques to solve the data imbalance problem but also show that the defect prediction model learned by the improved method in this paper has better prediction performance.

show abstract

Section: Current Status Of Researchmentioning

confidence: 99%

Deep Learning Software Defect Prediction Methods for Cloud Environments Research

Liu

Wang

2021

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Unfortunately, those methodologies will, in general, be "wait-and-see games;" they require viruses to be distinguished and available in the provisioned database before they can be halted, normally deciding new or "zeroday" exploits can go uncaught for some time. The fuzzy exploits monitor expects to find these obscure infections dependent on current PC conditions [3]. Therefore, the general level of security a framework can't be secured by somewhat perceiving the quantity of realized vulnerabilities existing in the framework.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Approach towards Assessment of Zero-day Attacks

Inzimam¹,

Chen²,

Zhang³

2019

IJCA

View full text Add to dashboard Cite

The biggest threat to the security of any organization is a zero-day attack, a large portion of the most significant organizations don't have a clue or notice the attack and thus, the contamination spread quicker before they can even respond. Zero-day attacks/threats are known as the most dangerous attack on the particular organization since they are startling. Though, the vast majority of the organizations previously set themselves up for known dangers and, zero-day attacks happen out of nowhere and are regularly occur by unknown intruders. Zero-day attacks cannot be detected from regular signature-based protections and thus represented a significant danger to corporate systems. It cannot be noticed until particular vulnerabilities are distinguished and detailed. It's very challenging to protect against zero-day attack yet sometime defense can't distinguish because of unknown signature and it performs action. Ensuring systems, applications, and frameworks from zero-day attacks are the overwhelming undertaking for an association's security. This method dissected the examination endeavors in connection to the recognition of zero-day attacks. The principal restrictions of existing methodologies are the signature-based of complicated operations and the false disturbing pace of unusual conduct. In order to fight this threat, the method proposed in this paper is to procedure framework for zero-day attack investigation and recognition. The framework detects the association's system and screens the conduct action of zero-day misuse at every single phase of their life cycle. The methodology in this paper gives a self-learning-based structure to detect arrange traffic that recognizes atypical conduct of the system to distinguish the nearness of zero-day exploitation. This structure utilizes administered arrangement plans for evaluation of known classes with the flexibility of self-characterization to recognize the new dimension of analysis.

show abstract

Association Rule-Mining-Based Intrusion Detection System With Entropy-Based Feature Selection

Devaraju¹,

Ramakrishnan²

2020

Handbook of Research on Intelligent Data Processing and Information Security Systems

View full text Add to dashboard Cite

Intrusion detection system (IDSs) are important to industries and organizations to solve the problems of networks, and various classifiers are used to classify the activity as malicious or normal. Today, the security has become a decisive part of any industrial and organizational information system. This chapter demonstrates an association rule-mining algorithm for detecting various network intrusions. The KDD dataset is used for experimentation. There are three input features classified as basic features, content features, and traffic features. There are several attacks are present in the dataset which are classified into Denial of Service (DoS), Probe, Remote to Local (R2L), and User to Root (U2R). The proposed method gives significant improvement in the detection rates compared with other methods. Association rule mining algorithm is proposed to evaluate the KDD dataset and dynamic data to improve the efficiency, reduce the false positive rate (FPR) and provides less time for processing.

show abstract

Fuzzy zero day exploits detector system

Cited by 5 publications

References 9 publications

Deep Learning Software Defect Prediction Methods for Cloud Environments Research

Deep Learning Software Defect Prediction Methods for Cloud Environments Research

An Efficient Approach towards Assessment of Zero-day Attacks

Association Rule-Mining-Based Intrusion Detection System With Entropy-Based Feature Selection

Contact Info

Product

Resources

About