• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1330-1339
• /
• 2022

3D object detection generally aims to detect relatively large data such as automobiles, buses, persons, furniture, etc, so it is vulnerable to small object detection. In addition, in an environment with limited resources such as embedded devices, it is difficult to apply the model because of the huge amount of computation. In this paper, the accuracy of small object detection was improved by focusing on local features using only one layer, and the inference speed was improved through the proposed knowledge distillation method from large pre-trained network to small network and adaptive quantization method according to the parameter size. The proposed model was evaluated using SUN RGB-D Val and self-made apple tree data set. Finally, it achieved the accuracy performance of 62.04% at mAP@0.25 and 47.1% at mAP@0.5, and the inference speed was 120.5 scenes per sec, showing a fast real-time processing speed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.132-138
• /
• 2012

Existing network layer firewall security support is one that does not support the higher layer, the application layer of a vulnerable web application security. Under these circumstances, the vulnerability of web applications to be able to defend a Web Application Firewall is positioned as a solver to solve the important security issues of businesses spotlighted in the next generation of security systems, and a very active market in the market other than domestic is expected to be formed. However, Firewall Web has not yet proposed a standard which can be used to test the performance of the Web Application Firewall Web Application Firewall and select the products of trust hardly Companies in BMT conduct their own individual problems and the cost of performance testing technologies, there is a limit. In this study, practically usable BMT model was developed to evaluate the firewall vendor. Product ratings ISO / IEC 9126, eight product characteristics meet the performance and characteristics of a web application firewall entries are derived. This can relieve the burden on the need to be evaluated in its performance testing of Web firewall, and can enhance the competitiveness of domestic-related sectors, by restoring confidence in the product can reduce the dependence on foreign products.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2023

Convolutional neural networks have already been applied to various fields beyond human visual processing capabilities in the image processing area. However, they are exposed to a severe risk of deteriorating model performance due to the appearance of adversarial attacks. In addition, defense technology to respond to adversarial attacks is effective against the attack but is vulnerable to other types of attacks. Therefore, to respond to an adversarial attack, it is necessary to analyze how the performance of the adversarial attack deteriorates through the process inside the convolutional neural network. In this study, the adversarial attack of the Alexnet and VGG11 models was analyzed using the population sparseness index, a measure of neuronal activity in neurophysiology. Through the research, it was observed in each layer that the population sparsity index for adversarial examples showed differences from that of benign examples.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.1-9
• /
• 2021

3D-NAND flash memory provides high capacity per unit area by stacking 2D-NAND cells having a planar structure. However, due to the nature of the lamination process, there is a problem that the frequency of error occurrence may vary depending on each layer or physical cell location. This phenomenon becomes more pronounced as the number of write/erase(P/E) operations of the flash memory increases. Most flash-based storage devices such as SSDs use ECC for error correction. Since this method provides a fixed strength of data protection for all flash memory pages, it has limitations in 3D NAND flash memory, where the error rate varies depending on the physical location. Therefore, in this paper, pages and layers with different error rates are classified into clusters through the K-means machine learning algorithm, and differentiated data protection strength is applied to each cluster. We classify pages and layers based on the number of errors measured after endurance test, where the error rate varies significantly for each page and layer, and add parity data to stripes for areas vulnerable to errors to provides differentiate data protection strength. We show the possibility that this differentiated data protection policy can contribute to the improvement of reliability and lifespan of 3D NAND flash memory compared to the protection techniques using RAID-like or ECC alone.

• Journal of Internet Computing and Services
• /
• v.9 no.2
• /
• pp.83-88
• /
• 2008

Session initiation protocol (SIP) is an application-layer prolocol to initiate and control multimedia client session. When client ask to use a SIP service, they need to be authenticated in order to get service from the server. Authentication in a SIP application is the process in which a client agent present credentials to another SIP element to establish a session or be granted access to the network service. In 2005, Yang et al. proposed a key exchange and authentication scheme for use in SIP applications, which is based on the Diffie-Hellman protocol. But, Yang et al.'s scheme is not suitable for the hardware-limited client and severs, since it requires the protocol participant to perform significant amount of computations (i.e., four modular exponentiations). Based on this observation. Huang and Wei have recently proposed a new efficient key exchange and authentication scheme thor improves on Yang et al.'s scheme. As for security, Huang and Wei claimed, among others, that their scheme is resistant to offline dictionary attacks. However, the claim turned out to be untrue. In this paper, we show thor Huang and Wei's key exchange and authentication scheme is vulnerable to on offline dictionary attack and forward secrecy.

• Journal of Ecology and Environment
• /
• v.46 no.4
• /
• pp.282-291
• /
• 2022

Background: The Arctic permafrost stores enormous amount of carbon (C), about one third of global C stocks. However, drastically increasing temperature in the Arctic makes the stable frozen C stock vulnerable to microbial decomposition. The released carbon dioxide from permafrost can cause accelerating C feedback to the atmosphere. Soil organic matter (SOM) composition would be the basic information to project the trajectory of C under rapidly changing climate. However, not many studies on SOM characterization have been done compared to quantification of SOM stocks. Thus, the purpose of our study is to determine soil properties and molecular compositions of SOM in four different Arctic regions. We collected soils in different soil layers from 1) Cambridge Bay, Canada, 2) Council, Alaska, USA, 3) Svalbard, Norway, and 4) Zackenberg, Greenland. The basic soil properties were measured, and the molecular composition of SOM was analyzed through pyrolysis-gas chromatography/mass spectrometry (py-GC/MS). Results: The Oi layer of soil in Council, Alaska showed the lowest soil pH and the highest electrical conductivity (EC) and SOM content. All soils in each site showed increasing pH and decreasing SOC and EC values with soil depth. Since the Council site was moist acidic tundra compared to other three dry tundra sites, soil properties were distinct from the others: high SOM and EC, and low pH. Through the py-GC/MS analysis, a total of 117 pyrolysis products were detected from 32 soil samples of four different Arctic soils. The first two-axis of the PCA explained 38% of sample variation. While short- and mid-hydrocarbons were associated with mineral layers, lignins and polysaccharides were linked to organic layers of Alaska and Cambridge Bay soil. Conclusions: We conclude that the py-GC/MS results separated soil samples mainly based on the origin of SOM (plants- or microbially-derived). This molecular characteristics of SOM can play a role of controlling SOM degradation to warming. Thus, it should be further investigated how the SOM molecular characteristics have impacts on SOM dynamics through additional laboratory incubation studies and microbial decomposition measurements in the field.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.79-85
• /
• 2022

Anomaly detection is a method to detect and block abnormal data flows in general users' data sets. The previously known method is a method of detecting and defending an attack based on a signature using the signature of an already known attack. This has the advantage of a low false positive rate, but the problem is that it is very vulnerable to a zero-day vulnerability attack or a modified attack. However, in the case of anomaly detection, there is a disadvantage that the false positive rate is high, but it has the advantage of being able to identify, detect, and block zero-day vulnerability attacks or modified attacks, so related studies are being actively conducted. In this study, we want to deal with these anomaly detection mechanisms, and we propose a new mechanism that performs both anomaly detection and classification while supplementing the high false positive rate mentioned above. In this study, the experiment was conducted with five configurations considering the characteristics of various algorithms. As a result, the model showing the best accuracy was proposed as the result of this study. After detecting an attack by applying the Extra Tree and Three-layer ANN at the same time, the attack type is classified using the Extra Tree for the classified attack data. In this study, verification was performed on the NSL-KDD data set, and the accuracy was 99.8%, 99.1%, 98.9%, 98.7%, and 97.9% for Normal, Dos, Probe, U2R, and R2L, respectively. This configuration showed superior performance compared to other models.

• Journal of the Korean GEO-environmental Society
• /
• v.22 no.12
• /
• pp.33-40
• /
• 2021

The deterioration of underground facilities, disturbance of the ground due to underground development activities, and changes in ground water can cause ground subsidence accidents in the urban areas. The investigation on the geotechnical and hydraulic factors affecting the ground subsidence accident is very significant to predict the ground subsidence risk in advance. In this study, an analysis DB was constructed through 3D ground modeling to utilize the currently operating geotechnical survey information DB and ground water behavior information for risk prediction. Additionally, using these results, the relationship between the actual ground subsidence occurrence history and ground conditions and ground water level changes was confirmed. Furthermore, the methodology used to visualize the risk of ground subsidence was presented by reconstructing the engineering characteristics of the soil presented according to the Unified Soil Classification System (USCS) in the existing geotechnical survey information into the internal erosion sensitivity of the soil, Based on the result, it was confirmed that the ground in the area where the ground subsidence occurred consists of more than 40% of sand (SM, SC, SP, SW) vulnerable to internal erosion. In addition, the effect of the occurrence frequency of ground subsidence due to the change in ground water level is also confirmed.

• Journal of the Korean earth science society
• /
• v.24 no.5
• /
• pp.428-439
• /
• 2003

Landslides, as a geological hazard, have caused extensive damage to property and sometimes result in loss of life. Thus, it is necessary to assess vulnerable areas for future possible landslides in order to mitigate the damage they cause. For this purpose, spatial data integration has been developed and applied to landslide hazard mapping. Among various models, this paper investigates and discusses the effectiveness of the Bayesian spatial data integration approach to landslide hazard mapping. In this study, several data sets related to landslide occurrences in Jangheung, Korea were constructed using GIS and then digitally represented using the likelihood ratio function. By computing the likelihood ratio, we obtained quantitative relationships between input data and landslide occurrences. The likelihood ratio functions were combined using the Bayesian combination rule. In order for predicted results to provide meaningful interpretations with respect to future landslides, we carried out validation based on the spatial partitioning of the landslide distribution. As a result, the Bayesian approach based on a likelihood ratio function can effectively integrate various spatial data for landslide hazard mapping, and it is expected that some suggestions in this study will be helpful to further applications including integration and interpretation stages in order to obtain a decision-support layer.

• Journal of KIISE:Information Networking
• /
• v.33 no.1
• /
• pp.38-48
• /
• 2006

For extending of hot-spot of WLAN, (2) proposes internetworking scheme between wireless LAN (WLAN) and mobile ad-hoc network (MANET), which employ the same layer-2 protocol with different mode. Compared to internetworking schemes between UMTS (Universal Mobile Telecommunications Systems) and WLAN (3-4), the scheme from (2) has relatively low overhead and latencies because WLAN and MANET are physically and logically similar to each other. However, the mode switching algorithm proposed in r2] for internetworking between WLAN and MANET only considers signal strength and determines handoff, and mobile nodes following a zigzag course in pollution area may perform handoff at short intervals. Furthermore, (2) employs mobile IPv6 (MIPv6) at base, which brings still high delay on handoff and overhead due to signal message exchange. In this paper, we present optimized internetworking scheme between WLAN and MANET, modified from (2). To settle ping-pong handoff from (2), we propose adaptive mode switching algorithm. HMIPv6 is employed for IP connectivity and mobility service in WLAN, which solves some shortcomings, such as high handoff overhead and vulnerable security. For routing in MANET, OLSR is employed, which is a proactive Protocol and has optimally reduced signal broadcasting overhead. OLSR operates with current P protocol compatibly with no change or modification. The proposed internetworking scheme based on adaptive mode switching algorithm shows better performance than scheme from (2).