• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.1087-1098
• /
• 2023

인공지능 기술의 급격한 발전으로 다양한 분야에서 적극적으로 활용되고 있으나, 이와 함께 인공지능 기반 시스템에 대한 공격 위협이 증가하고 있다. 특히, 딥러닝에서 사용되는 인공신경망은 입력 데이터를 고의로 변형시켜 모델의 오류를 유발하는 적대적 공격에 취약하다. 본 연구에서는 이미지에서 단 하나의 픽셀 정보만을 변형시킴으로써 시각적으로 인지하기 어려운 One-Pixel 공격으로부터 이미지 분류 모델을 보호하기 위한 방법을 제안한다. 제안된 방어 기법은 오토인코더 모델을 이용하여 분류 모델에 입력 이미지가 전달되기 전에 잠재적 공격 이미지에서 위협 요소를 제거한다. CIFAR-10 데이터셋을 이용한 실험에서 본 논문에서 제안하는 오토인코더 기반의 One-Pixel 공격 방어 기법을 적용한 사전 학습 이미지 분류 모델들은 기존 모델의 수정 없이도 One-Pixel 공격에 대한 강건성이 평균적으로 81.2% 향상되는 결과를 보였다.

• 실천공학교육논문지
• /
• 제16권3_spc호
• /
• pp.327-332
• /
• 2024

스마트 폰의 보급이 사용자에게 다양한 서비스를 제공하여 삶의 편리함을 주고 있다. 특히, 스마트 폰으로 사용자 인증 후에 손쉽게 온라인 금융거래가 이루어지고 있다. 사용자는 PIN을 이용한 인증으로 쉽게 서비스에 접근하지만 그로 인해 훔쳐보기나 레코딩과 같은 사회공학적 공격에 취약하다. 도어락에서 비밀번호 입력 시 허수를 포함하여 인증하는 방법을 스마트 폰에도 적용함으로써 사회공학적 공격에 대한 보안성을 높이고자 한다. 도어락은 PIN을 단말기 내에서 인증을 수행하지만 스마트 폰에서는 PIN 인증이 서버에서 처리하기 때문에 PIN 정보를 안전하게 전달해야 하는 문제가 있다. 제안기법을 통해 허수가 포함된 PIN을 여러 개 생성하여 해시값과 같은 가공값으로 전송하기 때문에 전송의 안정성을 보장하면서, 노출없이 PIN을 입력할 수 있는 기법으로 안전한 사용자 인증이 가능하다.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.101-112
• /
• 2024

Telugu language is considered as fourth most used language in India especially in the regions of Andhra Pradesh, Telangana, Karnataka etc. In international recognized countries also, Telugu is widely growing spoken language. This language comprises of different dependent and independent vowels, consonants and digits. In this aspect, the enhancement of Telugu Handwritten Character Recognition (HCR) has not been propagated. HCR is a neural network technique of converting a documented image to edited text one which can be used for many other applications. This reduces time and effort without starting over from the beginning every time. In this work, a Unicode based Handwritten Character Recognition(U-HCR) is developed for translating the handwritten Telugu characters into English language. With the use of Centre of Gravity (CG) in our model we can easily divide a compound character into individual character with the help of Unicode values. For training this model, we have used both online and offline Telugu character datasets. To extract the features in the scanned image we used convolutional neural network along with Machine Learning classifiers like Random Forest and Support Vector Machine. Stochastic Gradient Descent (SGD), Root Mean Square Propagation (RMS-P) and Adaptative Moment Estimation (ADAM)optimizers are used in this work to enhance the performance of U-HCR and to reduce the loss function value. This loss value reduction can be possible with optimizers by using CNN. In both online and offline datasets, proposed model showed promising results by maintaining the accuracies with 90.28% for SGD, 96.97% for RMS-P and 93.57% for ADAM respectively.

• Asia pacific journal of information systems
• /
• 제24권3호
• /
• pp.299-323
• /
• 2014

The reason location based service is drawing attention recently is because smart phones are being supplied increasingly. Smart phone, basically equipped with GPS that can identify location information, has the advantage that it can provide contents and services suitable for the user by identifying user location accurately. Offering such diverse advantages, location based services are increasingly used. In addition, for use of location based services, release of user's personal information and location data is essentially required. Regarding personal information and location data, in addition to IT companies, general companies also are conducting various profitable businesses and sales activities based on personal information, and in particular, personal location data, comprehending high value of use among personal information, are drawing high attentions. Increase in demand of personal information is raising the risk of personal information infringement, and infringements of personal location data also are increasing in frequency and degree. Therefore, infringements of personal information should be minimized through user's action and efforts to reinforce security along with Act on the Protection of Personal Information and Act on the Protection of Location Information. This study aimed to improve the importance of personal information privacy by empirically analyzing the effect of perceived values on the intention to strengthen location information security and continuously use location information for users who received location-based services (LBS) in mobile environments with the privacy calculation model of benefits and risks as a theoretical background. This study regarded situation-based provision, the benefit which users perceived while using location-based services, and the risk related to personal location information, a risk which occurs while using services, as independent variables and investigated the perceived values of the two variables. It also examined whether there were efforts to reduce risks related to personal location information according to the values of location- based services, which consumers perceived through the intention to strengthen security. Furthermore, it presented a study model which intended to investigate the effect of perceived values and intention of strengthening security on the continuous use of location-based services. A survey was conducted for three hundred ten users who had received location-based services via their smartphones to verify study hypotheses. Three hundred four questionnaires except problematic ones were collected. The hypotheses were verified, using a statistical method and a logical basis was presented. An empirical analysis was made on the data collected through the survey with SPSS 12.0 and SmartPLS 2.0 to verify respondents' demographic characteristics, an exploratory factor analysis and the appropriateness of the study model. As a result, it was shown that the users who had received location-based services were significantly influenced by the perceived value of their benefits, but risk related to location information did not have an effect on consumers' perceived values. Even though users perceived the risk related to personal location information while using services, it was viewed that users' perceived value had nothing to do with the use of location-based services. However, it was shown that users significantly responded to the intention of strengthening security in relation to location information risks and tended to use services continuously, strengthening positive efforts for security when their perceived values were high.

• 시큐리티연구
• /
• 제14호
• /
• pp.69-87
• /
• 2007

민간경비원의 조직공정성지각과 조직시민행동에 대해 분석한 연구결과는 다음과 같다. 우선 사회인구학적 특성 즉, 연령, 현재 회사 재직기간, 과거 총재직기간, 월수입에 따라 조직공정성은 차이를 보였다. 연령의 경우 분배공정성 지각에서 36세 이상 집단이 높고, 절차공정성 지각에서 31-35세 집단이 높게 나타났다. 따라서 연령이 많을수록 조직공정성 지각이 높게 나타났다. 현재 회사 재직기간에 따라서는 3년 1개월-5년 집단에서 분배공정성 지각과 절차공정성 지각 모두 높게 나타났다. 과거 총 재직기간에 따라서는 5년 1개월 이상 집단에서 분배공정성 지각과 절차공정성 지각 모두 높게 나타났다. 월수입에 따라서는 180만 원 이상 집단에서 분배공정성 지각과 절차공정성 지각 모두 높게 나타났다. 둘째, 사회인구학적 특성에 따라 조직시민행동은 차이를 보였다. 조직시민행동에서 연령에 따라서는 충성행동의 경우 연령이 많을수록 충성행동이 높았으며, 대인관계행동과 이타행동은 31-35세 집단에서 높게 나타났다. 현 회사 재직기간과 과거 총 재직기간에 따라서는 재직기간이 길수록 충성행동, 대인관계행동, 이타행동이 높게 나타났다. 월수입에 따라서는 월수입이 증가할수록 충성행동, 대인관계 행동, 이타행동이 높게 나타났다. 셋째, 민간경비원의 조직공정성 지각과 조직시민행동의 관계에 있어서는 회귀분석 결과, 절차공정성 지각이 각각의 변인인 충성행동과 대인관계행동 그리고 이타행동에 상대적으로 크게 영향을 미치는 것으로 나타났다. 따라서, 본 연구에서 제시했던 가설은 회귀분석 결과 모두 채택되었다. 이것은 조직공정성 지각이 향상되면 조직시민행동이 개선된다는 것을 시사한 것이다. 즉, 민간경비원이 조직내에서 공정성을 인지할 때 조직시민행동이 향상될 수 있다는 결론이 도출되었다.

• 정보처리학회논문지C
• /
• 제10C권3호
• /
• pp.295-304
• /
• 2003

기존의 보안관점은 악의적인 사용자의 공격이나 우발적인 사고로부터 프로그램과 데이터의 보호를 강조한다. 이를 위한 방화벽, 침입탐지시스템의 연구개발은 성숙 단계에 접어들었다. 최근들어 새롭게 대두되고 있는 침입감내 개념은 정보 생존성을 위한 마지막 방어선으로 공격이 성공하더라도 임무 수행에 필수적인 시스템의 중요 서비스를 계속 제공하기 위해 가용성과 무결성을 강조하는 개념이다. 본 논문에서는 침입감내 시스템을 프로그램 보호와 데이터 보호관점에서 분류하고 프로그램과 데이터의 침입감내 특성을 모두 지원하는 통합된 침입감내 프레임워크를 제안한다.

• Plant Biotechnology Reports
• /
• 제5권2호
• /
• pp.107-120
• /
• 2011

The ability to feed an expanding world population poses one of the greatest challenges to mankind in the future. Accompanying the increased demand for food by the expected nine billion inhabitants of Earth in 2050 will be a continual decrease in arable land area, together with a decline in crop yield due to a variety of stresses. For these formidable challenges to be met, future crops should not only by high-yielding, but also stress-tolerant and disease-resistant. In this review, we highlight the importance of genetic engineering as an indispensable tool to generate just such future crops. We briefly discuss strategies and available tools for biotechnological crop improvement and identify selected examples of candidate genes that may be manipulated so that current biological maxima in yield may be surpassed by comfortable margins. Future prospects and the necessity for basic research aimed at identifying novel target genes are also discussed.

• Journal of Preventive Medicine and Public Health
• /
• 제45권5호
• /
• pp.277-282
• /
• 2012

Field epidemiology involves the implementation of quick and targeted public health interventions with the aid of epidemiological methods. In this article, we share our practical experiences in outbreak management and in safeguarding the population against novel diseases. Given that cities represent the financial nexuses of the global economy, global health security necessitates the safeguard of cities against epidemic diseases. Singapore's public health landscape has undergone a systemic and irreversible shift with global connectivity, rapid urbanization, ecological change, increased affluence, as well as shifting demographic patterns over the past two decades. Concomitantly, the threat of epidemics, ranging from severe acute respiratory syndrome and influenza A (H1N1) to the resurgence of vector-borne diseases as well as the rise of modern lifestyle-related outbreaks, have worsened difficulties in safeguarding public health amidst much elusiveness and unpredictability. One critical factor that has helped the country overcome these innate and man-made public health vulnerabilities is the development of a resilient field epidemiology service, which includes our enhancement of surveillance and response capacities for outbreak management, and investment in public health leadership. We offer herein the Singapore story as a case study in meeting the challenges of disease control in our modern built environment.

• ETRI Journal
• /
• 제35권3호
• /
• pp.448-458
• /
• 2013

This paper presents a generalized post-processing technique for enhancing the pseudorandomness of digital chaotic oscillators through a nonlinear XOR-based operation with rotation and feedback. The technique allows full utilization of the chaotic output as pseudorandom number generators and improves throughput without a significant area penalty. Digital design of a third-order chaotic system with maximum function nonlinearity is presented with verified chaotic dynamics. The proposed post-processing technique eliminates statistical degradation in all output bits, thus maximizing throughput compared to other processing techniques. Furthermore, the technique is applied to several fully digital chaotic oscillators with performance surpassing previously reported systems in the literature. The enhancement in the randomness is further examined in a simple image encryption application resulting in a better security performance. The system is verified through experiment on a Xilinx Virtex 4 FPGA with throughput up to 15.44 Gbit/s and logic utilization less than 0.84% for 32-bit implementations.