• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.64-72
• /
• 2024

In recent times cyber attackers can use Artificial Intelligence (AI) to boost the sophistication and scope of attacks. On the defense side, AI is used to enhance defense plans, to boost the robustness, flexibility, and efficiency of defense systems, which means adapting to environmental changes to reduce impacts. With increased developments in the field of information and communication technologies, various exploits occur as a danger sign to cyber security and these exploitations are changing rapidly. Cyber criminals use new, sophisticated tactics to boost their attack speed and size. Consequently, there is a need for more flexible, adaptable and strong cyber defense systems that can identify a wide range of threats in real-time. In recent years, the adoption of AI approaches has increased and maintained a vital role in the detection and prevention of cyber threats. In this paper, an Ensemble Deep Restricted Boltzmann Machine (EDRBM) is developed for the classification of cybersecurity threats in case of a large-scale network environment. The EDRBM acts as a classification model that enables the classification of malicious flowsets from the largescale network. The simulation is conducted to test the efficacy of the proposed EDRBM under various malware attacks. The simulation results show that the proposed method achieves higher classification rate in classifying the malware in the flowsets i.e., malicious flowsets than other methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.3
• /
• pp.165-172
• /
• 2006

There are various threats as side effects against the growth of information technology, and malicious codes such as Internet worms may bring about confusions to upset a national backbone network. In this paper, we examine the existed spreading models and propose a new worm spreading model on Internet environment. We also predict and analyze the spreading effects of high-speed Internet worms. The proposed model leads to a better prediction of the worm spreading since various factors are considered.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.469-471
• /
• 2002

인터넷의 급속한 발전은 우리 생활의 많은 변화를 가져왔다. 특히 사용상의 편리함과 유용성으로 인해 컴퓨터를 전공하지 않은 사랑도 쉽게 접속하여 사용할 수 있게 됨에 따라 악의적인 사용자도 증가하기 시작하였다. 따라서 본문에서는 악의적인 사용자의 접근을 차단할 수 있는 침입 차단 시스템을 설계하고 침입 차단 시스템의 취약점인 TCP Hijacking, IP Spoofing등에도 견딜 수 있는 침입 차단 시스템의 패킷필터링 모듈을 제안한다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.4 no.1
• /
• pp.33-40
• /
• 2008

This paper presents a new scheduling scheme in wireless distributed network. To overcome the limited information about unfamiliar mobile nodes and to reduce the required system performance, we propose a scheduling algorithm of job allocation based on the trust model. The suggested scheduler evaluate an unfamiliar mobile node's trust and make reference to the trust value of neighboring scheduler. This scheduling algorithm can avoid malicious or selfish mobile nodes by assigning low trust values. We also present a trust evaluation metric and show the efficiency of suggested scheduling algorithm by performance evaluation.

• Journal of Magnetics
• /
• v.22 no.2
• /
• pp.196-202
• /
• 2017

The occurrence of ferroresonance in electrical systems including nonlinear inductors such as transformers will bring a lot of malicious damages. The intense ferromagnetic saturation of the iron core is the most influential factor in ferroresonance that makes nonsinusoidal current and voltage. So the nonlinear behavior modeling of the magnetic core is the most important challenge in the study of ferroresonance. In this paper, the ferroresonance phenomenon is investigated in a single phase transformer using the finite element method and considering the hysteresis loop. Jiles-Atherton (JA) inverse vector model is used for modeling the hysteresis loop, which provides the accurate nonlinear model of the transformer core. The steady-state analysis of ferroresonance is done while considering different capacitors in series with the no-load transformer. The accurate results from copper losses and iron losses are extracted as the most important specifications of transformers. The validity of the simulation results is confirmed by the corresponding experimental measurements.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.101-109
• /
• 2019

In addition to enabling access, database accounts play a protective role by defending the database from external attacks. However, because only a single account is used in the database, the account becomes the subject of vulnerability attacks. This common practice is due to the lack of database support, large numbers of users, and row-based database permissions. Therefore if the logic of the application is wrong or vulnerable, there is a risk of exposing the entire database. In this paper, we propose a Least-Privilege Account Separation Model (LPASM) that serves as an information guardian to protect the database from attacks. We separate database accounts depending on the role of application services. This model can protect the database from malicious attacks and prevent damage caused by privilege escalation by an attacker. We classify the account control policies into four categories and propose detailed roles and operating plans for each account.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.264-267
• /
• 2022

Recently, federated learning (FL) has increased prominence as a viable approach for enhancing user privacy and data security by allowing collaborative multi-party model learning without exchanging sensitive data. Despite this, most present FL systems still depend on a centralized aggregator to generate a global model by gathering all submitted models from users, which could expose user privacy and the risk of various threats from malicious users. To solve these issues, we suggested a safe FL framework that employs differential privacy to counter membership inference attacks during the collaborative FL model training process and empowers blockchain to replace the centralized aggregator server.

• Convergence Security Journal
• /
• v.10 no.1
• /
• pp.9-17
• /
• 2010

Internet network routing system is used to prevent spread and distribution of malicious data traffic. The penetration of malicious code and the function of security blocking are performed on the same course of traffic pathway. The security architecture is the concept to distinguish the architecture from the group handling with the traffic on the structure of network which is performed with the function of penetration and security. The security architecture could be different from the criterion of its realm and function, which requires the development and the application of security mechanism for every architecture. For the establishment of security architecture it is needed to show what criterion of net work should be set up. This study is based on analysis of diagnostic weakness structure in the network security architecture and research the criterion for topology factor, security architecture structure map selection, and blocking location and disinfection net. It is shown to increase the effective rate blocking the virus with the proposed method in this paper rather than the traditional network architecture.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1375-1380
• /
• 2021

Korea's security response to application service app is still insufficient due to the initial opening of the public safety network. Therefore, preemptive security measures are essential. In this study, we proposed to establish a 'public safety network app security system' to prevent potential vulnerabilities to the app store that distributes app in public safety network and android operating system that operate app on dedicated terminal devices. In order for an application service app to be listed on the public safety network mobile app store, a dataset of malicious and normal app is first established to extract characteristics and select the most effective AI model to perform static and dynamic analysis. According to the analysis results, 'Safety App Certificate' is certified for non-malicious app to secure reliability for listed apps. Ultimately, it minimizes the security blind spots of public safety network app. In addition, the safety of the network can be secured by supporting public safety application service of certified apps.