• Title/Summary/Keyword: Security Label

Search Result 47, Processing Time 0.028 seconds

A Nested Named Entity Recognition Model Robust in Few-shot Learning Environments using Label Information (라벨 정보를 이용한 Few-shot Learning 환경에 강건한 중첩 개체명 인식 모델)

  • Hyunsun Hwang;Changki Lee;Wooyoung Go;Myungchul Kang
    • Annual Conference on Human and Language Technology
    • /
    • 2023.10a
    • /
    • pp.622-626
    • /
    • 2023
  • 중첩 개체명 인식(Nested Named Entity Recognition)은 하나의 개체명 표현 안에 다른 개체명 표현이 들어 있는 중첩 구조의 개체명을 인식하는 작업으로, 중첩 개체명 인식을 위한 학습데이터 구축 작업은 일반 개체명 인식 학습데이터 구축보다 어렵다는 문제가 있다. 본 논문에서는 이러한 문제를 해결하기 위해 Few-shot Learning 환경에 강건한 중첩 개체명 인식 모델을 제안한다. 이를 위해, 기존의 Biaffine 중첩 개체명 인식 모델의 출력 레이어를 라벨 의미 정보를 활용하도록 변경하여 학습데이터가 적은 환경에서 중첩 개체명 인식의 성능을 향상시키도록 하였다. 실험 결과 GENIA 중첩 개체명 인식 데이터의 5-shot, 10-shot, 20-shot 환경에서 기존의 Biaffine 모델보다 평균 10%p이상의 높은 F1-measure 성능을 보였다.

  • PDF

Design of an Effective Deep Learning-Based Non-Profiling Side-Channel Analysis Model (효과적인 딥러닝 기반 비프로파일링 부채널 분석 모델 설계방안)

  • Han, JaeSeung;Sim, Bo-Yeon;Lim, Han-Seop;Kim, Ju-Hwan;Han, Dong-Guk
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.30 no.6
    • /
    • pp.1291-1300
    • /
    • 2020
  • Recently, a deep learning-based non-profiling side-channel analysis was proposed. The deep learning-based non-profiling analysis is a technique that trains a neural network model for all guessed keys and then finds the correct secret key through the difference in the training metrics. As the performance of non-profiling analysis varies greatly depending on the neural network training model design, a correct model design criterion is required. This paper describes the two types of loss functions and eight labeling methods used in the training model design. It predicts the analysis performance of each labeling method in terms of non-profiling analysis and power consumption model. Considering the characteristics of non-profiling analysis and the HW (Hamming Weight) power consumption model is assumed, we predict that the learning model applying the HW label without One-hot encoding and the Correlation Optimization (CO) loss will have the best analysis performance. And we performed actual analysis on three data sets that are Subbytes operation part of AES-128 1 round. We verified our prediction by non-profiling analyzing two data sets with a total 16 of MLP-based model, which we describe.

PRISM: A Preventive and Risk-reducing Integrated Security Management Model using Security Label (PRISM: 보안 레이블을 이용한 위험예방 통합보안관리 모델)

  • Kim, Dong-Soo;Kim, Tae-Kyung;Chung, Tai-Myoung
    • The KIPS Transactions:PartC
    • /
    • v.10C no.6
    • /
    • pp.815-824
    • /
    • 2003
  • Many organizations operate security systems and manage them using the intergrated secutity management (ISM) dechnology to secyre their network environment effectively. But current ISM is passive and behaves post-event manner. To reduce cost and resource for managing security and to remove possbility of succeeding in attacks by intruder, the perventive security management technology is required. In this paper, we propose PRISM model that performs preventative security management with evaluating the security level of host or network and the sensitivity level of information asset from potential risks before security incidents occur. The PRISM can give concrete and effective security management in managing the current complex networks.

Performance Comparison of Gas Leak Region Segmentation Based on Transfer Learning (Transfer Learning 기법을 이용한 가스 누출 영역 분할 성능 비교)

  • Marshall, Marshall;Park, Jang-Sik;Park, Seong-Mi
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.23 no.3
    • /
    • pp.481-489
    • /
    • 2020
  • Safety and security during the handling of hazardous materials is a great concern for anyone in the field. One driving point in the security field is the ability to detect the source of the danger and take action against it as quickly as possible. Via the usage of a fully convolutional network, it is possible to create the label map of an input image, indicating what object is occupying the specific area of the image. This research employs the usage of U-net, which was constructed in biomedical field segmentation to segment cells, instead of the original FCN. One of the challenges that this research faces is the availability of ground truth with precise labeling for the dataset. Testing the network after training resulted in some images where the network pronounces even better detail than the expected label map. With better detailed label map, the network might be able to produce better segmentation is something to be studied in further research.

A study on the comparison of VPN with Dedicated Line Network on security (보안측면에서의 가상사설망과 전용회선망의 비교 연구)

  • Jeong, Eun-Hee;Lee, Byung-Kwan
    • The Journal of Korea Institute of Information, Electronics, and Communication Technology
    • /
    • v.1 no.2
    • /
    • pp.107-122
    • /
    • 2008
  • Communication is be classified into public network and private network. VPN is made by integrating the circuit cost reduction of public network and the reliable security support of public network. This paper analyzes the IPSec using three layer tunneling, MPLS(Multi Protocol Label Switching) integrating 2 layer switching and 3 layer routing techniques and dedicated line from the viewpoint of security. In conclusion, VPN is better than dedicated network line in cost and security. If IPSec VPN is compared with MPLS VPN, MPLS VPN is more excellent than IPSec VPN in safe data transmission, cost, QoS and management.

  • PDF

An Efficient Deep Learning Ensemble Using a Distribution of Label Embedding

  • Park, Saerom
    • Journal of the Korea Society of Computer and Information
    • /
    • v.26 no.1
    • /
    • pp.27-35
    • /
    • 2021
  • In this paper, we propose a new stacking ensemble framework for deep learning models which reflects the distribution of label embeddings. Our ensemble framework consists of two phases: training the baseline deep learning classifier, and training the sub-classifiers based on the clustering results of label embeddings. Our framework aims to divide a multi-class classification problem into small sub-problems based on the clustering results. The clustering is conducted on the label embeddings obtained from the weight of the last layer of the baseline classifier. After clustering, sub-classifiers are constructed to classify the sub-classes in each cluster. From the experimental results, we found that the label embeddings well reflect the relationships between classification labels, and our ensemble framework can improve the classification performance on a CIFAR 100 dataset.

Unified Labeling and Fine-Grained Verification for Improving Ground-Truth of Malware Analysis (악성코드 분석의 Ground-Truth 향상을 위한 Unified Labeling과 Fine-Grained 검증)

  • Oh, Sang-Jin;Park, Leo-Hyun;Kwon, Tae-Kyoung
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.29 no.3
    • /
    • pp.549-555
    • /
    • 2019
  • According to a recent report by anti-virus vendors, the number of new and modified malware increased exponentially. Therefore, malware analysis research using machine learning has been actively researched in order to replace passive analysis method which has low analysis speed. However, when using supervised learning based machine learning, many studies use low-reliability malware family name provided by the antivirus vendor as the label. In order to solve the problem of low-reliability of malware label, this paper introduces a new labeling technique, "Unified Labeling", and further verifies the malicious behavior similarity through the feature analysis of the fine-grained method. To verify this study, various clustering algorithms were used and compared with existing labeling techniques.

A Study on Satisfaction and Healthy Eating Index in Subjects of Nutrition-Plus Program focusing Seodaemun-gu in Seoul (영양플러스 대상자의 만족도와 식생활 평가에 대한 연구 - 서울 서대문구 지역 대상자를 중심으로 -)

  • Rha, Young Ah;Park, Jin Young;Kim, Jung Yun
    • Culinary science and hospitality research
    • /
    • v.22 no.8
    • /
    • pp.172-181
    • /
    • 2016
  • This study evaluated the satisfaction and healthy eating index of nutrition-plus program providing nutritional supplements to pregnancy, lactating women, infant and children. This program was carried out at Public Healthcare Center, Seodaemun-gu in Seoul from February 2014 to June 2014. The subject selected among applicants for low income family financing of the government included 159 subjects. There was no statistically significant difference for degree of satisfaction with supplementary food by age, but the degree tends to get higher at lower age. Degree of satisfaction with supplementary food by the duration for participation was shown higher as the duration gets longer. For questions of 'Do you check nutrition label?' and 'Do you preserve food as described at food label?' in healthy eating index evaluation, the scores appeared higher at younger age group as they check the nutrition label more. Also as the duration for participation gets longer, the scores appeared higher which can be interpreted as effect of nutrition education from Nutrition-Plus. Frequency of having breakfast gets lower at higher age of subjects. And it gets higher as the duration for participation gets longer even though that there's no difference between '3 to 4 months' and '5 to 8 months' of the duration of participation. For evaluation of food security in recent 1 year, 86.8% of subjects responded 'Food sufficiency' and 'Enough but not always the kinds of food we want', and there is no difference by age and the duration of participation. As a result of this research, it is shown that the subjects of nutrition support project are relatively satisfied with the support. And healthy eating index gets improved as the duration of participation gets longer which can be considered as effect of nutrition education. It seems to be necessary to keep nutrition education as well as food support so to perform food life education on appropriate purchase and consumption of food.

A Study on Path Selection Scheme for Fast Restoration in Multilayer Networks (신속한 다계층 보호 복구를 위한 경로선택 방식 연구)

  • Cho, Yang-Hyun;Kim, Hyun-Cheol
    • Convergence Security Journal
    • /
    • v.12 no.3
    • /
    • pp.35-43
    • /
    • 2012
  • The explosive growth of Internet traffic cause by smart equipment such as smart phone has led to a dramatic increase in demand for data transmission capacity and network control architecture, which requires high transmission rates beyond the conventional transmission capability. Next generation networks are expected to be controlled by Generalized Multi-Protocol Label Switching(GMPLS) protocol suite and operating at multiple switching layers. In order to ensure the most efficient utilization of multilayer network resources, effective global provisioning that providing the network with the possibility of reacting in advance to traffic changes should be provided. In this paper, we proposes a new path selection scheme in multilayer optical networks based on the vertical PCE architecture and a different approach to efficiently exploit multiple PCE cooperation.

K-Means Clustering with Deep Learning for Fingerprint Class Type Prediction

  • Mukoya, Esther;Rimiru, Richard;Kimwele, Michael;Mashava, Destine
    • 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.