دانلود مقاله سیستم تشخیص نفوذ مرکب جدید (CIDS) برای WSN
خلاصه
مقدمه
II. پیشینه کار پیشنهادی
III. توپولوژی پیشنهادی
IV. نتایج و بحث
نتیجه گیری
منابع
Abstract
I. INTRODUCTION
II. BACKGROUND OF THE PROPOSED WORK
III. PROPOSED TOPOLOGY
IV. RESULTS AND DISCUSSION
V. CONCLUSION
References
چکیده
فن آوری بی سیم مدرن نیازمند اجرای گره های حسگر از پیش تعیین شده برای یک شبکه بی سیم ساختار یافته است. این شبکه دارای گره های حسگر برای نظارت یا سنجش محیطی است که داده ها را به صورت بی سیم به یک نقطه جمع آوری منتقل می کند. بنابراین، انتقال داده ها باید با جلوگیری از حملات نفوذ خارجی محافظت شود. این امر با طراحی یک سیستم تشخیص نفوذ موثر که به عنوان سیستم تشخیص نفوذ مرکب (CIDS) پیشنهاد شده است، انجام خواهد شد. برای شبکه ای در ساختار شبکه ناهمگن با قابلیت شناسایی حملات خارجی مانند سیل داده ها، ارسال بسته های داده ناخواسته و تغییر گره مقصد مناسب است. برای مسیریابی بسته های داده بین گره ها از حداقل مصرف توان با روش سرفصل خوشه های متغیر استفاده می شود. فعالیت‌های گره‌های حسگر نظارت می‌شود و مجموعه داده‌ای بر اساس فعالیت گره تشکیل می‌شود. به عنوان پایگاه داده شبکه (NDB) شناخته می شود. با استفاده از این مجموعه داده، حملات نفوذ با استفاده از شبکه عصبی مصنوعی (ANN) شناسایی خواهند شد. ANN با یک مجموعه داده از پیش تعریف شده برای شناسایی موثر حملات خارجی آموزش داده خواهد شد. روش پیشنهادی CIDS دقت بالایی در شناسایی حملات خارجی به شبکه‌های حسگر را در مقایسه با سیستم طراحی‌شده قبلی در همه انواع حملات نشان می‌دهد.
Abstract
Modern wireless technology demands the implementation of preset Sensor nodes for a structured wireless network. The network has sensor nodes for surveillance or environmental sensing, which wirelessly transmit data to a collection point. Therefore, data transfer must be protected by preventing external intrusion attacks. This will be handled by designing an effective intrusion detection system proposed as a Composite Intrusion detection system (CIDS). It is suitable for a network in heterogeneous network structure with a capable of identifying externals attacks like flooding of data's, sending unwanted data packets and changing the destination node. For routing of data packets between the nodes, minimum power utilization with changeable cluster heading method is used. The activities of sensor nodes will be monitored and a dataset is formed on the basis of the node’s activity. It is known as Network Databases (NDB). Using this dataset, the intrusion attacks will be identified by using Artificial Neural Network (ANN). ANN will be trained with a predefined dataset for the effective identification of external attacks. The proposed CIDS methodology shows the high accuracy of identifying the external attacks on the sensor networks when comparing to the previous designed system in all the types of attacks.
INTRODUCTION
Wireless based sensors networks is a revolutionary invention in the modern era used for all types of application like surveillance in military application, collection of healthrelated data in medical field [1]. It has set of distribution sensor nodes in an application area for sensing the data with a predefined geographic location. The location of nodes will be decided on the basis of XY co-ordinates. The sensor nodes have to collect the sensing data from their corresponding location and passed to a cluster head. The head nodes will make effective data aggregation method and passed the concern data to base station [2]. The data transmission will be done by using any of the routing protocols and it should be secured from the external threat. Also, the power backup of the sensor is a tradeoff between the data transmission and securing the data from the threats [4]. The data packets routing is depicted in figure 1.
As the sensor nodes are in open area and the data transmission will be carried over in an open platform with limited network resources, the chances on injection of threats will be high. In spite the position of nodes is a heterogeneous network, chances on threats will be high [5].
CONCLUSION
The fundamental purpose of the CIDS is to identify external threats and their nature before they penetrate the network's structure. As a result of the excellent implementation of data packet routing, detection is performed efficiently with the aid of a changing cluster heading node and low power consumption of sensor nodes. As the CIDS identify risks utilizing artificial neural networks, its efficiency is superior to that of existing specified research networks. The sort of external attacks recognized by the planned CIDS flooding of Data's unscheduled data transmission is a significant factor. This is because data flooding reduces network efficiency and causes a significant amount of network resources to be squandered. By providing the correct data set during the training phase of neural networks, this threat detection can be modified. This is done on a periodic basis to acquire the node activity dataset. Therefore, the suggested system is capable of identifying external threats and their categories in the shortest time possible, with advance notification to all other networks on the sorts of threats found.