• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.726-730
• /
• 2009

The proliferation of the web and digital photography has drastically increased multimedia data and has resulted in the need of the high quality internet service based on the moving picture like user generated contents(UGC). The keyword-based search on large scale images and video collections is too expensive and requires much manual intervention. Therefore the web search engine may provide the content-based retrieval on the multimedia data for search accuracy and customer satisfaction. In this paper, we propose a novel distributed index structure based on multiple length signature files according to data distribution. In addition, we describe how our scalable index technique can be used to find the nearest neighbors in the cluster environments.

• Convergence Security Journal
• /
• v.22 no.5
• /
• pp.145-154
• /
• 2022

Recently, the widespread proliferation and high sophistication of botnets are having serious consequences not only for enterprises and users, but also for cyber warfare between countries. Therefore, research to detect botnets is steadily progressing. However, the DGA-based botnet has a high detection rate with the existing signature and statistics-based technology, but also has a high limit in the false positive rate. Therefore, in this paper, we propose a detection model using text-based n-gram to detect DGA-based botnets. Through the proposed model, the detection rate, which is the limit of the existing detection technology, can be increased and the false positive rate can also be minimized. Through experiments on large-scale domain datasets and normal domains used in various DGA botnets, it was confirmed that the performance was superior to that of the existing model. It was confirmed that the false positive rate of the proposed model is less than 2 to 4%, and the overall detection accuracy and F1 score are both 97.5%. As such, it is expected that the detection and response capabilities of DGA-based botnets will be improved through the model proposed in this paper.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.613-621
• /
• 2019

Recently, with the development of the Internet of Things (IoT) and cloud computing technologies, security threats have increased as malicious codes infect IoT devices, and new malware spreads ransomware to cloud servers. In this study, we propose a threat-detection technique that checks obfuscated script patterns to compensate for the shortcomings of conventional signature-based and behavior-based detection methods. Proposed is a malicious code-detection technique that is based on malicious script-pattern analysis that can detect zero-day attacks while maintaining the existing detection rate by registering and checking derived distribution patterns after analyzing the types of malicious scripts distributed through websites. To verify the performance of the proposed technique, a prototype system was developed to collect a total of 390 malicious websites and experiment with 10 major malicious script-distribution patterns derived from analysis. The technique showed an average detection rate of about 86% of all items, while maintaining the existing detection speed based on the detection rule and also detecting zero-day attacks.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.3
• /
• pp.555-564
• /
• 2022

Recently, cyberattacks are using hacking techniques utilizing intelligent and advanced malicious codes for non-face-to-face environments such as telecommuting, telemedicine, and automatic industrial facilities, and the damage is increasing. Traditional information protection systems, such as anti-virus, are a method of detecting known malicious URLs based on signature patterns, so unknown malicious URLs cannot be detected. In addition, the conventional static analysis-based malicious URL detection method is vulnerable to dynamic loading and cryptographic attacks. This study proposes a technique for efficiently detecting malicious URLs by dynamically learning malicious URL data. In the proposed detection technique, malicious codes are classified using machine learning-based feature selection algorithms, and the accuracy is improved by removing obfuscation elements after preprocessing using Weighted Euclidean Distance(WED). According to the experimental results, the proposed machine learning-based malicious URL detection technique shows an accuracy of 89.17%, which is improved by 2.82% compared to the conventional method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.615-627
• /
• 2024

With the evolution of power systems and advancements in IT technology, there is an increasing demand to shift from serial-based communication to TCP/IP-based communication. However, TCP/IP communication entails various security threats, necessitating extensive consideration from an information security perspective. Security measures such as authentication and encryption cannot be rapidly implemented due to issues like the replacement of Remote Terminal Units (RTUs) and the performance requirements of encryption algorithms. This paper proposes a state estimation-based intrusion detection model to identify and effectively detect threats to power control systems in such a context. The proposed model, in addition to signature detection methods, verifies the validity of acquired data, enabling it to detect attacks that are difficult to identify using traditional methods, such as data tampering.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1311-1319
• /
• 2019

Currently, the web environment is a commonly used area for sharing information and conducting business. It is becoming an attack point for external hacking targeting on personal information leakage or system failure. Conventional signature-based detection is used in cyber threat but signature-based detection has a limitation that it is difficult to detect the pattern when it is changed like polymorphism. In particular, injection attack is known to the most critical security risks based on web vulnerabilities and various variants are possible at any time. In this paper, we propose a novelty detection technique to detect abnormal state that deviates from the normal state on web-server log dataset(WSLD). The proposed method is a machine learning-based technique to detect a minor anomalous data that tends to be different from a large number of normal data after replacing strings in web-server log dataset with vectors using machine learning-based embedding algorithm.

• Journal of KIISE
• /
• v.43 no.5
• /
• pp.596-605
• /
• 2016

Since the Denial of Service Attack against multiple targets in the Korean network in private and public sectors in 2009, Korea has spent a great amount of its budget to build strong Internet infrastructure against DDoS attacks. As a result of the investments, many major governments and corporations installed dedicated DDoS defense systems. However, even organizations equipped with the product based defense system often showed incompetency in dealing with DDoS attacks with little variations from known attack types. In contrast, by following a capacity centric DDoS detection method, defense personnel can identify various types of DDoS attacks and abnormality of the system through checking availability of service resources, regardless of the types of specific attack techniques. Thus, the defense personnel can easily derive proper response methods according to the attacks. Deviating from the existing DDoS defense framework, this research study introduces a capacity centric DDoS detection methodology and provides methods to mitigate DDoS attacks by applying the methodology.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.65-72
• /
• 2021

Recently, attacks on the network environment have been rapidly escalating and intelligent. Thus, the signature-based network intrusion detection system is becoming clear about its limitations. To solve these problems, research on machine learning-based intrusion detection systems is being conducted in many ways, but two problems are encountered to use machine learning for intrusion detection. The first is to find important features associated with learning for real-time detection, and the second is the imbalance of data used in learning. This problem is fatal because the performance of machine learning algorithms is data-dependent. In this paper, we propose the HSF-DNN, a network intrusion detection model based on a deep neural network to solve the problems presented above. The proposed HFS-DNN was learned through the NSL-KDD data set and performs performance comparisons with existing classification models. Experiments have confirmed that the proposed Hybrid Feature Selection algorithm does not degrade performance, and in an experiment between learning models that solved the imbalance problem, the model proposed in this paper showed the best performance.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.15-26
• /
• 2022

Various subjects are carrying out cyberattacks using a variety of tactics and techniques. Additionally, cyberattacks for political and economic purposes are also being carried out by groups which is sponsored by its nation. To deal with cyberattacks, researchers used to classify the malware family and the subjects of the attack based on malware signature. Unfortunately, attackers can easily masquerade as other group. Also, as the attack varies with subject, techniques, and purpose, it is more effective for defenders to identify the attacker's purpose and goal to respond appropriately. The essential goal of cyberattacks is to threaten the information security of the target assets. Information security is achieved by preserving the confidentiality, integrity, and availability of the assets. In this paper, we relabel the attacker's goal based on MITRE ATT&CK® in the point of CIA triad as well as classifying cyber security reports to verify the labeling method. Experimental results show that the model classified the proposed CIA label with at most 80% probability.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.287-294
• /
• 2016

APT attack aimed at the interruption of information and communication facilities and important information leakage of companies. it performs an attack using zero-day vulnerabilities, social engineering base on collected information, such as IT infra, business environment, information of employee, for a long period of time. Fragmentary response to cyber threats such as malware signature detection methods can not respond to sophisticated cyber-attacks, such as APT attacks. In this paper, we propose a cyber intrusion detection model for countermeasure of APT attack by utilizing heterogeneous system log into big-data. And it also utilizes that merging pattern-based detection methods and abnormality detection method.