KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Settings

Subject: search.filters.subject.Intruder detection

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Intruder Detection by Using Faster R-CNN in Power Substation
    (2020-01-01)
    Srijakkot, Krit
    ;
    Kanjanasurat, Isoon
    ;
    Wiriyakrieng, Nuttakan
    ;
    Lartwatechakul, Mayulee
    ;
    Benjangkaprasert, Chawalit
    This paper presents the intruder detection by using the Faster R-CNN model and administrator system for the power substation in Khon Kaen substation 4 of the Electricity Generating Authority of Thailand (EGAT). There are two processes of intruder detection-detecting the intruder and sending a notification to the system administrator of EGAT through Line application. The Faster R-CNN model of intruder detection was trained and tested by using the Open Image Dataset and our dataset. We collected our dataset of 1,500 images from a different condition from the real environment. There are two conditions, including distance and light intensity. Our system used a high-performance computer by using GPU: Nvidia Titan RTX 24 GB to support the object detection system from using five cameras at the same time. The performance of intruder detection achieved by greater than 95%.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Detecting sinkhole attack and selective forwarding attack in wireless sensor networks
    (2009-12-01)
    Tumrongwittayapak, Chanatip
    ;
    Varakulsiripunth, Ruttikorn
    Security in Wireless Sensor Networks (WSNs) is especially challenging and quite different from traditional network security mechanisms. There are two major reasons. Firstly, there are severe constraints on these devices namely their minimal energy, computational and communicational capabilities. Secondly, there is an additional risk of physical attacks such as node capture and tampering. Moreover, cryptography based techniques alone are insufficient to secure WSNs [1]. Hence, intrusion detection techniques must be designed to detect the attacks. Further, these techniques should be lightweight because of resource-constrained nature of WSNs [2]. In this paper, we present a new approach of robust and lightweight solution for detecting the Sinkhole attack and the Selective Forwarding attack based on Received Signal Strength Indicator (RSSI) readings of messages. The proposed solution needs collaboration of some Extra Monitor (EM) node apart from the ordinary nodes. We use RSSI value from four EM nodes to determine the position of all sensor nodes which the Base Station (BS) is origin position (0,0). Later, we use this information as weight from the BS. Another functions of EM nodes are eavesdropper and monitor all traffics, in order to detect the Selective Forwarding attack in the network. Our solution is lightweight in the sense that monitor nodes were not loaded any ordinary nodes or BS and not cause a communication overhead. ©2009 IEEE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Detecting sinkhole attacks in wireless sensor networks
    (2009-12-01)
    Tumrongwittayapak, Chanatip
    ;
    Varakulsiripunth, Ruttikorn
    Presently, the wireless sensor networks (WSNs) are widely used in many areas of communication systems and its security system becomes very important. However, the security mechanism for WSNs has to be considered differently from traditional network. Firstly, there are severe constraints on WSNs devices such as minimal energy, computational and communicational capabilities. Secondly, there is an additional risk of physical attacks such as node capture and tampering. Moreover, cryptography based techniques alone are insufficient to secure WSNs. Hence, intrusion detection techniques must be designed and developed to detect the any kind of undesirable attacks. Further, these techniques should be lightweight because of resource-constrained nature of WSNs. Therefore, we present a new approach of robust and lightweight solution for detecting the Sinkhole attack based on Received Signal Strength Indicator (RSSI) readings of messages. The proposed solution needs collaboration of some Extra Monitor (EM) nodes apart from the ordinary nodes. We use values of RSSI from four EM nodes to determine the position of all sensor nodes where the Base Station (BS) is located at origin position (0,0). We use this information as weight from the BS in order to detect Sinkhole attack. The simulation results show that the proposed mechanism is lightweight due to the monitor nodes were not loaded with any ordinary nodes or BS. Moreover, the proposed mechanism does not cause the communication overhead. © 2009 SICE.