ترجمه مقاله نقش ضروری ارتباطات 6G با چشم انداز صنعت 4.0
- مبلغ: ۸۶,۰۰۰ تومان
ترجمه مقاله پایداری توسعه شهری، تعدیل ساختار صنعتی و کارایی کاربری زمین
- مبلغ: ۹۱,۰۰۰ تومان
As network attacks have increased in number and severity over the past few years, Intrusion Detection Systems (IDSs) have become a necessary addition to the security infrastructure of most organizations. These systems are software or hardware schemes that automate the process of monitoring events that occur in a computer system or network and analyzing them for signs of security problems (Crothers, 2003; Bace and Mell, 2001). Deploying highly effective IDS systems is extremely challenging. For instance until an IDS is properly tuned to a specific environment, there will be thousands of alerts generated daily. Although most of these alerts are incorrect and thus are false alerts, it is not obvious whether the alert is positive or negative until they have been investigated. There have been many techniques proposed to lessen these false alerts and improve the performance of the system. Agarwal and Joshi (2000) used a two-stage general-to specific framework for learning a rule-based model (PNrule). This model can classify models of a data set that has widely different class distributions in the training data set. Levin (2000) used a data-mining tool for classification of data and prediction of new cases using automatically generated decision trees. In this paper will show that the use of Bayesian probability is very promising in reducing the false positive alert rate. Bayesian probability is an interpretation of the probability calculus which holds that the concept of a probability can be defined as the degree to which a person (or community) believes that proposition is true. Currently Bayesian theory is used in email spam-filters (Grapham, 2004; Issac et al., 2009; Alkabani et al., 2006), Speech recognition (Chien et al., 2006), Pattern Recognition (Shi and Manduchi, 2003), and Intrusion Detection (Kruegel et al., 2003; Cemerlic et al., 2008; Mehdi et al., 2007).