Signature-based Intrusion detection systems are not suitable anymore to be used in nowadays network environment. Because signature-based models are not able to detect new threats and unknown attacks. Due to technology improvement, the number of attacks is increasing exponentially. Statistics show that attacks number increases with a rate of 100% each year causing huge money loss, about tens of millions of dollars for ransomware attacks only. This high number of millions of new threats that are developed every day, reduces the effectiveness of signature-based IDS because it is not a practical solution to update the signatures databases every few minutes. Anomaly-based IDS can be a better alternative of signature-based IDS because it is more suitable for nowadays Abstract Anomaly-based Intrusion Detection System (IDS) has been a hot research topic because of its ability to detect new threats rather than only memorized signatures threats of signature-based IDS. Especially after the availability of advanced technologies that increase the number of hacking tools and increase the risk impact of an attack. The problem of any anomaly-based model is its high false-positive rate. The high false-positive rate is the reason why anomaly IDS is not commonly applied in practice. Because anomaly-based models classify an unseen pattern as a threat where it may be normal but not included in the training dataset. This type of problem is called overfitting where the model is not able to generalize. Optimizing Anomaly-based models by having a big training dataset that includes all possible normal cases may be an optimal solution but could not be applied in practice. Although we can increase the number of training samples to include much more normal cases, still we need a model that has more ability to generalize. In this research paper, we propose applying deep model instead of traditional models because it has more ability to generalize. Thus, we will obtain less false-positive by using big data and deep model. We made a comparison between machine learning and deep learning algorithms in the optimization of anomaly-based IDS by decreasing the false-positive rate. We did an experiment on the NSL-KDD benchmark and compared our results with one of the best used classifiers in traditional learning in IDS optimization. The experiment shows 10% lower false-positive by using deep learning instead of traditional learning.
Recently, we have seen lots of real-life examples of attacks' huge impacts in different domains such as politics and economics. Hacking has become more critical and more dangerous than ever before. The number of hacking attacks is growing exponentially every few months. That means signature-based IDS is not useful anymore as we cannot update it with new signatures every few minutes. Also with developing technologies attacks become more sophisticated, APT attacks are more common than ever before.
Link prediction in social networks has been an active field of study in recent years fueled by the rapid growth of many social networks. Many link prediction methods are harmed by users’ intention of avoiding being traced across networks. They may provide inaccurate information or overlook a great deal of information in multiple networks. This problem was overcome by developing methods for predicting links in a network based on known links in another network. Node alignment between the two networks significantly improves the efficiency of those methods. This research proposes a new embedding method to improve link prediction and node alignment results. The proposed embedding method is based on the Expanded Graph, which is our new novel network that has edges from both networks in addition to edges across the networks. Matrix factorization on the Finite Step Transition and Laplacian similarity matrices of the Expanded Graph has been used to obtain the embeddings for the nodes. Using the proposed embedding techniques, we jointly run network alignment and link prediction tasks iteratively to let them optimize each other’s results. We performed extensive experiments on many datasets to examine the proposed method. We achieved significant improvements in link prediction precision, which was 50% better than the peer’s method, and in recall, which was 500% better in some datasets. We also scale down the processing time of the solution to be more applicable to big social networks. We conclude that computed embedding in this type of problem is more suitable than learning the embedding since it shortens the processing time and gives better results.
Active and deductive rules in databases and procedural attachment in knowledge bases are used as mechanisms of computation of derived attributes. These research domains have become very closely related. The support of derivations in current active databases suffers from many semantic and technical problems. Active rules in their ECA (Event Condition Action) form are event oriented whereas derivations are naturally data oriented. Deductive rules are well adapted to relational databases, but their integration within the object oriented model does not always have successful results. Procedural attachment may be considered as both a deductive and active process, but it uses an imperative language to derive attributes. In this paper, we try to focus on the use of active rules to derive attributes in an object oriented model. We give our approach for the support of deductions in a declarative assertion language and their processing in an active way. We propose a declarative derivation approach integrated within an object oriented model. IntoductionAn active database is a database which can automatically carry out some predefined actions in response to some specific events when the corresponding conditions are satisfied [15] [20]. Active databases appeared when researchers in the database field recognized the use of the integration of production rules in relational DBMSs [27]. Most active database models use an ECA approach in which when the event occurs the condition is tested, if it is satisfied, the action is executed. These rules have their roots in artificial intelligence with the languages of expert systems such as OPS5[lo]. They have been justified as a suitable framework for the specification of queries, views, integrity constraints, and triggers in databases [22]. In contrast, these rules are not the best choice to support derivations, which are naturally data oriented. The values of derived attributes are expressed as functions of values of other attributes. The computation tools of these attributes are invoked when the attributes they depend on are modified. The use of active rules for supporting derivations does not take advantage of this dependency relationship between derived attributes and the other attributes. Meanwhile, using another mechanism, we can take advantage of this dependency, for better performance at the design and execution levels, and to be able to analyse an application behaviour by determining the consequences of each modification. Deductive databases constitute a declarative natural manner to enrich relational databases by intelligent processing (deduction). The origin of deductive databases goes back to work on theorem proving [25][31]. They were introduced as extensions of relational databases by logic. Deduced facts are the logical consequences of the previous facts using the specified deduction rules. The integration of these rules and the object oriented models creates impedance mismatch problems [16]. In fact, the object oriented concepts are difficult t o introduce in the deductiv...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.