• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.29-36
• /
• 2022

In deep learning classification tasks, most models frequently assume that all labels are available for the training datasets. As such strategies to learn new concepts from unlabeled datasets are scarce. In fingerprint classification tasks, most of the fingerprint datasets are labelled using the subject/individual and fingerprint datasets labelled with finger type classes are scarce. In this paper, authors have developed approaches of classifying fingerprint images using the majorly known fingerprint classes. Our study provides a flexible method to learn new classes of fingerprints. Our classifier model combines both the clustering technique and use of deep learning to cluster and hence label the fingerprint images into appropriate classes. The K means clustering strategy explores the label uncertainty and high-density regions from unlabeled data to be clustered. Using similarity index, five clusters are created. Deep learning is then used to train a model using a publicly known fingerprint dataset with known finger class types. A prediction technique is then employed to predict the classes of the clusters from the trained model. Our proposed model is better and has less computational costs in learning new classes and hence significantly saving on labelling costs of fingerprint images.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.182-190
• /
• 2021

Deep learning is an advanced technology for large-scale data analysis, with numerous promising cases like image processing, object detection and significantly more. It becomes customarily to use transfer learning and fine-tune a pre-trained CNN model for most image recognition tasks. Having people taking photos and tag themselves provides a valuable resource of in-data. However, these tags and labels might be noisy as people who annotate these images might not be experts. This paper aims to explore the impact of noisy labels on fine-tuning pre-trained CNN models. Such effect is measured on a food recognition task using Food101 as a benchmark. Four pre-trained CNN models are included in this study: InceptionV3, VGG19, MobileNetV2 and DenseNet121. Symmetric label noise will be added with different ratios. In all cases, models based on DenseNet121 outperformed the other models. When noisy labels were introduced to the data, the performance of all models degraded almost linearly with the amount of added noise.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.3-8
• /
• 2023

Multi-domain optical transport networks are not fundamentally interoperable and require an integrated orchestration mechanism and path provision mechanism at the entire network level. In addition, ensuring network survivability is one of the important issues. MPLS-TP (Multi-Protocol Label Switching-Transport Profile) defines various protection/recovery methods as standards, but does not mention how to calculate and select protection/recovery paths. Therefore, an algorithm that minimizes protection/recovery collisions at the optical circuit packet integrated network level and calculates and sets a path that can be rapidly protected/recovered over the entire integrated network area is required. In this paper, we proposed an algorithm that calculates and sets up a path that can be rapidly protected and restored in a T-SDN network composed of multiple ring-mesh topology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.702-723
• /
• 2020

The application of machine learning (ML) in intrusion detection has attracted much attention with the rapid growth of information security threat. As an efficient multi-label classifier, kernel extreme learning machine (KELM) has been gradually used in intrusion detection system. However, the performance of KELM heavily relies on the kernel selection. In this paper, a novel multiple kernel extreme learning machine (MKELM) model combining the ReliefF with nature-inspired methods is proposed for intrusion detection. The MKELM is designed to estimate whether the attack is carried out and the ReliefF is used as a preprocessor of MKELM to select appropriate features. In addition, the nature-inspired methods whose fitness functions are defined based on the kernel alignment are employed to build the optimal composite kernel in the MKELM. The KDD99, NSL and Kyoto datasets are used to evaluate the performance of the model. The experimental results indicate that the optimal composite kernel function can be determined by using any heuristic optimization method, including PSO, GA, GWO, BA and DE. Since the filter-based feature selection method is combined with the multiple kernel learning approach independent of the classifier, the proposed model can have a good performance while saving a lot of training time.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.65-75
• /
• 2017

The Detection Model is the model to find the result of a certain purpose using artificial intelligent, data mining, intelligent algorithms In Cyber Security, it usually uses to detect intrusion, malwares, cyber incident, and attacks etc. There are an amount of unlabeled data that are collected in a real environment such as security data. Since the most of data are not defined the class labels, it is difficult to know type of data. Therefore, the label determination process is required to detect and analysis with accuracy. In this paper, we proposed a KDFL(K-means and D-S Fusion based Labeling) method using D-S inference and k-means(unsupervised) algorithms to decide label of data records by fusion, and a detection model architecture using a proposed labeling method. A proposed method has shown better performance on detection rate, accuracy, F1-measure index than other methods. In addition, since it has shown the improved results in error rate, we have verified good performance of our proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.2B
• /
• pp.144-156
• /
• 2003

Internet/Intranet has been continuously enhanced by new emerging IP technologies such as differentiate service(DiffServ), IPSec(IP Security) and MPLS(Multi-protocol Label Switching) traffic engineering. According to the increased demands of various real-time multimedia services, ISP(Internet Service Provider) should provide enhanced end-to-end QoS(quality of service) and security features. Therefore, Internet and Intranet need the management functionality of sophisticated traffic engineering functions. In this paper, we design and implement the performance management functionality for the guaranteed end-to-end QoS provisioning on MPLS-based VPLS(Virtual Private LAN Service). We propose VPLS OAM(Operation, Administration and Maintenance) for efficient performance management. We focus on a scheme of QoS management and measurement of QoS parameters(such as delay, jitter, loss, etc.) using VPLS OAM functions. The proposed performance management system also supports performance tuning to enhance the provided QoS by re-adjusting the bandwidth of LSPs for VPLS. We present the experimental results of performance monitoring and analysis using a network simulator.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.4
• /
• pp.967-974
• /
• 1998

Access control scheme of the firewall systems protects the systems from threats by using the conventional discretionary access control mechanism. The discretionary access control mechanism is insufficient to control secure information flow on the multievel network. Thus, it is necessary to provide the mandatory access control mechanism to the firewall systems for the multilevel security environment. In this paper, we present a design scheme of the security mechanisms concerning the sensitivity label and the mandatory access control for securely processing the multilevel information.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.3
• /
• pp.84-90
• /
• 2000

This paper presents a design of an access control mechanism that can resolves the complicated problems of access control requirements in internet environment. In this paper, we proposed an access control mechanism which can satisfy the combined goals of confidentiality integrity and availability of any resource. We defined an access control mechanism from the viewpoints of identity-based, rule-based and role-based policy and implemented 6 access control operations. The Proposed access control mechanism can protect resources from unauthorized accesses based on the multi-level security policies of security label, integrity level, role and ownership.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.33-40
• /
• 2023

Machine-learning techniques are discovering effective performance on data analytics. Classification and regression are supported for prediction on different kinds of data. There are various breeds of classification techniques are using based on nature of data. Threshold determination is essential to making better model for unlabelled data. In this paper, threshold value applied as range, based on min-max normalization technique for creating labels and multiclass classification performed on rainfall data. Binary classification is applied on autism data and classification techniques applied on child abuse data. Performance of each technique analysed with the evaluation metrics.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.1038-1041
• /
• 2007

어플리케이션 또는 네트워크 레벨의 외곽 방어에 의한 보안 기능의 한계로 인하여 운영체제 내부 보안에 대한 필요성이 증대되고 있다. 그에 따라 시스템상에서의 또는 시스템에 의한 행동을 제어하기 위한 차세대 보안솔루션으로 보안 운영체제가 부각되고 있다. 이에 본 논문에서는 안전한 운영체제 구축을 위한 보안 요구 사항의 기준이 될 수 있는 다중등급 보안에 의한 윈도우 서버 보안 강화 기술을 소개하고 본 논문에서 설계하고 구현한 보안 커널의 기능을 중심으로 기술한다. 또한 기존의 전형적인 보안레이블을 확장하여 추가적으로 제어할 수 있도록 수정된 보안 모델을 제시한다.