• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.762-765
• /
• 2010

크래커(Cracker)의 공격으로부터 내부 자원을 보호하기 위한 허니팟 시스템은 크게 두 가지로 구분된다. 하나는 내부 정보자원을 보호하기 위해 크래커의 공격을 유인하는 목적의 허니팟이며, 다른 하나는 방어기법을 연구하기 위해 크래커의 공격을 유도한 후 공격기법을 로그기반으로 수집하는 허니팟이다. 하지만, 최근의 공격은 크래커로 인한 공격보다는 불특정 다수를 공격하기 위해 대량의 악성코드를 통한 공격이 주를 이루고 있다. 따라서, 허니팟의 유형도 변화가 필요하게 되었다. 악성코드에 대한 방어기법을 연구하는 Anti-Virus 연구소에서는 최근의 악성코드 공격으로부터 시스템을 보호하기 위해서는 악성코드를 조기에 수집하는 것이 주요 이슈로 등장하게 되었다. 악성코드 수집을 위한 허니팟은 기존 허니팟과 다른 특징을 가지고 있으며, 이러한 특징을 고려하여 개발되어야 한다. 하지만, 악성코드 수집용 허니팟이 필수적으로 갖추어야 할 조건이 정의된 것이 없으며, 개발을 위한 구현 모델이 존재하지 않아, 실제 구축에는 어려움을 겪고 있다. 따라서, 본 고에서는 기존 허니팟과 비교를 통해 악성코드 수집용 허니팟이 갖추어야 할 7 대 요구조건을 개발하고, 이를 토대로 기존에 제시된 적이 없는 악성코드 수집용 허니팟 구현 모델을 제안하였다. Anti-Virus 연구소들은 본 구현모델을 통해 악성코드 수집용 허니팟을 개발하여, 확산되는 악성코드를 조기에 수집 및 대응함으로써, 1.25 대란, 7.7 DDoS 대란과 같이 악성코드로 인해 발생하는 국가적 정보자산 손실을 미연에 방지하는데 큰 기여를 할 것으로 기대된다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.1
• /
• pp.127-132
• /
• 2024

With the rapid evolution of the Internet, the application of artificial intelligence fields is more and more extensive, and the era of AI has come. At the same time, adversarial attacks in the AI field are also frequent. Therefore, the research into adversarial attack security is extremely urgent. An increasing number of researchers are working in this field. We provide a comprehensive review of the theories and methods that enable researchers to enter the field of adversarial attack. This article is according to the "Why? → What? → How?" research line for elaboration. Firstly, we explain the significance of adversarial attack. Then, we introduce the concepts, types, and hazards of adversarial attack. Finally, we review the typical attack algorithms and defense techniques in each application area. Facing the increasingly complex neural network model, this paper focuses on the fields of image, text, and malicious code and focuses on the adversarial attack classifications and methods of these three data types, so that researchers can quickly find their own type of study. At the end of this review, we also raised some discussions and open issues and compared them with other similar reviews.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.179-191
• /
• 2024

With the advancement of modern technology, cyber-attacks are always rising. Specialized defense systems are needed to protect organizations against these threats. Malicious behavior in the network is discovered using security tools like intrusion detection systems (IDS), firewall, antimalware systems, security information and event management (SIEM). It aids in defending businesses from attacks. Delivering advance threat feeds for precise attack detection in intrusion detection systems is the role of cyber-threat intelligence (CTI) in the study is being presented. In this proposed work CTI feeds are utilized in the detection of assaults accurately in intrusion detection system. The ultimate objective is to identify the attacker behind the attack. Several data sets had been analyzed for attack detection. With the proposed study the ability to identify network attacks has improved by using machine learning algorithms. The proposed model provides 98% accuracy, 97% precision, and 96% recall respectively.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.591-614
• /
• 2019

With the proliferation of social media, it has become easier for people to spread rumors online, which can aggravate the issues arising from online rumors. There are many individuals and organizations that are adversely affected by malicious online rumors. Despite their importance, there has been little research into why and how people spread rumors online, thus inhibiting the understanding of factors that affect the spreading of online rumors. With attention seeking to address this gap, this paper draws upon the dual process theory and the de-individuation theory to develop a theoretical model of factors affecting the spreading of an online rumor, and then empirically tests it using survey data from 211 individuals about a specific rumor. The results indicate that the perceived credibility of the rumor affects the individuals' attitudes toward spreading it, which consequently affects the rumor spreading behavior. Vividness, confirmation of prior beliefs, argument strength, and source credibility positively influence the perceived credibility of online rumors. Finally, anonymity moderates the relationship between attitude toward spreading online rumors and the spreading behavior.

• Journal of Intelligence and Information Systems
• /
• v.13 no.3
• /
• pp.119-140
• /
• 2007

Recommender systems enable a user to decide which information is interesting and valuable in our world of information overload. As the recent studies of distributed computing environment have been progressing actively, recommender systems, most of which were centralized, have changed toward a peer-to-peer approach. Collaborative Filtering (CF), one of the most successful technologies in recommender systems, presents several limitations, namely sparsity, scalability, cold start, and the shilling problem, in spite of its popularity. The move from centralized systems to distributed approaches can partially improve the issues; distrust of recommendation and abuses of personal information. However, distributed systems can be vulnerable to attackers, who may inject biased profiles to force systems to adapt their objectives. In this paper, we consider both effective CF in P2P environment in order to improve overall performance of system and efficient solution of the problems related to abuses of personal data and attacks of malicious users. To deal with these issues, we propose a multi-agent framework for a distributed CF focusing on the trust relationships between individuals, i.e. web of trust. We employ an agent-based approach to improve the efficiency of distributed computing and propagate trust information among users with effect. The experimental evaluation shows that the proposed method brings significant improvement in terms of the distributed computing of similarity model building and the robustness of system against malicious attacks. Finally, we are planning to study trust propagation mechanisms by taking trust decay problem into consideration.

• KNOM Review
• /
• v.23 no.2
• /
• pp.18-28
• /
• 2020

With the development of the virtual community, the benefits that IT technology provides to people in fields such as healthcare, industry, communication, and culture are increasing, and the quality of life is also improving. Accordingly, there are various malicious attacks targeting the developed network environment. Firewalls and intrusion detection systems exist to detect these attacks in advance, but there is a limit to detecting malicious attacks that are evolving day by day. In order to solve this problem, intrusion detection research using machine learning is being actively conducted, but false positives and false negatives are occurring due to imbalance of the learning dataset. In this paper, a Random Oversampling method is used to solve the unbalance problem of the UNSW-NB15 dataset used for network intrusion detection. And through experiments, we compared and analyzed the accuracy, precision, recall, F1-score, training and prediction time, and hardware resource consumption of the models. Based on this study using the Random Oversampling method, we develop a more efficient network intrusion detection model study using other methods and high-performance models that can solve the unbalanced data problem.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.517-521
• /
• 2008

A worm is a malware that propagates quickly from host to host without any human intervention. Need of early worm detection has changed research paradigm from signature based worm detection to the behavioral based detection. To increase effectiveness of proposed solution, in this paper we present mechanism of detection and prevention of worm in distributed fashion. Furthermore, to minimize the worm destruction; upon worm detection we propagate the possible attack aleγt to neighboring nodes in secure and organized manner. Considering worm behavior, our proposed mechanism detects worm cycles and infection chains to detect the sudden change in network performance. And our model neither needs to maintain a huge database of signatures nor needs to have too much computing power, that is why it is very light and simple. So, our proposed scheme is suitable for the ubiquitous environment. Simulation results illustrate better detection and prevention which leads to the reduction of infection rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.5
• /
• pp.2427-2445
• /
• 2016

In contrast to traditional "store-and-forward" routing mechanisms, network coding offers an elegant solution for achieving maximum network throughput. The core idea is that intermediate network nodes linearly combine received data packets so that the destination nodes can decode original files from some authenticated packets. Although network coding has many advantages, especially in wireless sensor network and peer-to-peer network, the encoding mechanism of intermediate nodes also results in some additional security issues. For a powerful adversary who can control arbitrary number of malicious network nodes and can eavesdrop on the entire network, cryptographic signature schemes provide undeniable authentication mechanisms for network nodes. However, with the development of quantum technologies, some existing network coding signature schemes based on some traditional number-theoretic primitives vulnerable to quantum cryptanalysis. In this paper we first present an efficient network coding signature scheme in the standard model using lattice theory, which can be viewed as the most promising tool for designing post-quantum cryptographic protocols. In the security proof, we propose a new method for generating a random lattice and the corresponding trapdoor, which may be used in other cryptographic protocols. Our scheme has many advantages, such as supporting multi-source networks, low computational complexity and low communication overhead.

• Journal of Digital Convergence
• /
• v.17 no.7
• /
• pp.285-292
• /
• 2019

With the popularization of PC, SNS and IoT, a lot of data is generated and the amount is increasing exponentially. Artificial neural network learning is a topic that attracts attention in many fields in recent years by using huge amounts of data. Artificial neural network learning has shown tremendous potential in speech recognition and image recognition, and is widely applied to a variety of complex areas such as medical diagnosis, artificial intelligence games, and face recognition. The results of artificial neural networks are accurate enough to surpass real human beings. Despite these many advantages, privacy problems still exist in artificial neural network learning. Learning data for artificial neural network learning includes various information including personal sensitive information, so that privacy can be exposed due to malicious attackers. There is a privacy risk that occurs when an attacker interferes with learning and degrades learning or attacks a model that has completed learning. In this paper, we analyze the attack method of the recently proposed neural network model and its privacy protection method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.181-192
• /
• 2022

The emergence of new malware is incapacitating existing signature-based malware detection techniques., and applying various anti-analysis techniques makes it difficult to analyze. Recent studies related to signature-based malware detection have limitations in that malware creators can easily bypass them. Therefore, in this study, we try to build a machine learning model that can detect and classify the anti-analysis techniques of packers applied to malware, not using the characteristics of the malware itself. In this study, the n-gram opcodes are extracted from the malicious binary to which various anti-analysis techniques of the commercial packers are applied, and the features are extracted by using TF-IDF, and through this, each anti-analysis technique is detected and classified. In this study, real-world malware samples packed using The mida and VMProtect with multiple anti-analysis techniques were trained and tested with 6 machine learning models, and it constructed the optimal model showing 81.25% accuracy for The mida and 95.65% accuracy for VMProtect.