• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.25-36
• /
• 2023

Today, as AI (Artificial Intelligence) technology is introduced in various fields, including security, the development of technology is accelerating. However, with the development of AI technology, attack techniques that cleverly bypass malicious behavior detection are also developing. In the classification process of AI models, an Adversarial attack has emerged that induces misclassification and a decrease in reliability through fine adjustment of input values. The attacks that will appear in the future are not new attacks created by an attacker but rather a method of avoiding the detection system by slightly modifying existing attacks, such as Adversarial attacks. Developing a robust model that can respond to these malware variants is necessary. In this paper, we propose two methods of generating Adversarial attacks as efficient Adversarial attack generation techniques for improving Robustness in AI models. The proposed technique is the XAI-based attack technique using the XAI technique and the Reference based attack through the model's decision boundary search. After that, a classification model was constructed through a malicious code dataset to compare performance with the PGD attack, one of the existing Adversarial attacks. In terms of generation speed, XAI-based attack, and reference-based attack take 0.35 seconds and 0.47 seconds, respectively, compared to the existing PGD attack, which takes 20 minutes, showing a very high speed, especially in the case of reference-based attack, 97.7%, which is higher than the existing PGD attack's generation rate of 75.5%. Therefore, the proposed technique enables more efficient Adversarial attacks and is expected to contribute to research to build a robust AI model in the future.

• Convergence Security Journal
• /
• v.20 no.1
• /
• pp.41-47
• /
• 2020

In the corporate information system environment, detecting and controlling suspicious behaviors occurring at the end point of the actual business application is the most important area to secure the organization's business environment. In order to accurately detect and block threats from inside and outside, it is necessary to be able to monitor all areas of all terminals in the organization and collect relevant information. In other words, in order to maintain a secure business environment of a corporate organization from the constant challenge of malicious code, everything that occurs in a business terminal such as a PC beyond detection and defense-based client security based on known patterns, signatures, policies, and rules that have been universalized in the past. The introduction of an EDR solution to enable identification and monitoring is now an essential element of security. In this study, we will look at the essential functions required for EDR solutions, and also study the design and development plans of smart EDR systems based on active and proactive detection of security threats.

• The KIPS Transactions:PartC
• /
• v.12C no.6 s.102
• /
• pp.855-864
• /
• 2005

In this paper, we propose an intrusion detection system(IDS) architecture which can detect and respond against the generation of abnormal traffic such as malicious code and Internet worms. We model the system, design and implement a simulator using OPNET Modeller, for the performance analysis on the response capacity of alert information in the proposed system. At first, we model the arrival process of alert information resulted from abnormal traffic. In order to model the situation in which alert information is intensively produced, we apply the IBP(Interrupted Bernoulli Process) which may represent well the burstiness of traffic. Then we perform the simulation in order to gain some quantitative understanding of the system for our performance parameters. Based on the results of the performance analysis, we analyze factors which may hinder in accelerating the speed of security node, and would like to present some methods to enhance performance.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.519-529
• /
• 2019

Nowadays, intelligent Android malware applies anti-analysis techniques to hide malicious behaviors and make it difficult for anti-virus vendors to detect its presence. Malware can use background components to hide harmful operations, use activity-alias to get around with automation script, or wipe the logcat to avoid forensics. During our study, several static analysis tools can not extract these hidden components like main activity, and dynamic analysis tools also have problem with code coverage due to partial execution of android malware. In this paper, we design and implement a system to analyze intelligent malware that uses anti-analysis techniques to improve detection rate of evasive malware. It extracts the hidden components of malware, runs background components like service, and generates all the intent events defined in the app. We also implemented a real-time logging system that uses modified logcat to block deleting logs from malware. As a result, we improve detection rate from 70.9% to 89.6% comparing other container based dynamic analysis platform with proposed system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.2
• /
• pp.37-47
• /
• 2011

In the recent years, malicious codes called malware are having shown significant increase due to the code obfuscation to evade detection mechanisms. When the code obfuscation technique is applied to malwares, they can change their instruction sequence and also even their signature. These malwares which have same functionality and different appearance are able to evade signature-based AV products. Thus, AV venders paid large amount of cost to analyze and classify malware for generating the new signature. In this paper, we propose a novel approach for detecting metamorphic malwares. The proposed mechanism first converts malware's API call sequences to call graph through dynamic analysis. After that, the callgraph is converted to semantic signature using 128 abstract nodes. Finally, we extract all subgraphs and analyze how similar two malware's behaviors are through subgraph similarity. To validate proposed mechanism, we use 273 real-world malwares include obfuscated malware and analyze 10,100 comparison results. In the evaluation, all metamorphic malwares are classified correctly, and similar module behaviors among different malwares are also discovered.

• Journal of Information Processing Systems
• /
• v.3 no.2
• /
• pp.43-53
• /
• 2007

The use of agent paradigm in today's applications is hampered by the security concerns of agents and hosts alike. The agents require the presence of a secure and trusted execution environment; while hosts aim at preventing the execution of potentially malicious code. In general, hosts support the migration of agents through the provision of an agent server and managing the activities of arriving agents on the host. Numerous studies have been conducted to address the security concerns present in the mobile agent paradigm with a strong focus on the theoretical aspect of the problem. Various proposals in Intrusion Detection Systems aim at securing hosts in traditional client-server execution environments. The use of such proposals to address the security of agent hosts is not desirable since migrating agents typically execute on hosts as a separate thread of the agent server process. Agent servers are open to the execution of virtually any migrating agent; thus the intent or tasks of such agents cannot be known a priori. It is also conceivable that migrating agents may wish to hide their intentions from agent servers. In light of these observations, this work attempts to bridge the gap from theory to practice by analyzing the security mechanisms available in Aglet. We lay the foundation for implementation of application specific protocols dotted with access control, secured communication and ability to detect tampering of agent data. As agents exists in a distributed environment, our proposal also introduces a novel security framework to address the security concerns of hosts through collaboration and pattern matching even in the presence of differing views of the system. The introduced framework has been implemented on the Aglet platform and evaluated in terms of accuracy, false positive, and false negative rates along with its performance strain on the system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3230-3253
• /
• 2017

Android malware steals users' private information, and embedded unsafe advertisement (ad) libraries, which execute unsafe code causing damage to users. The majority of such traffic is HTTP and is mixed with other normal traffic, which makes the detection of malware and unsafe ad libraries a challenging problem. To address this problem, this work describes a novel HTTP traffic flow mining approach to detect and categorize Android malware and unsafe ad library. This work designed AndroCollector, which can automatically execute the Android application (app) and collect the network traffic traces. From these traces, this work extracts HTTP traffic features along three important dimensions: quantitative, timing, and semantic and use these features for characterizing malware and unsafe ad libraries. Based on these HTTP traffic features, this work describes a supervised classification scheme for detecting malware and unsafe ad libraries. In addition, to help network operators, this work describes a fine-grained categorization method by generating fingerprints from HTTP request methods for each malware family and unsafe ad libraries. This work evaluated the scheme using HTTP traffic traces collected from 10778 Android apps. The experimental results show that the scheme can detect malware with 97% accuracy and unsafe ad libraries with 95% accuracy when tested on the popular third-party Android markets.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.6
• /
• pp.1431-1439
• /
• 2017

In the security field, log analysis is important to detect malware or abnormal behavior. Recently, image visualization techniques for malware dectection becomes to a major part of security. These techniques can also be used in online games. Users can leave a game when they felt bad experience from game bot, automatic hunting programs, malicious code, etc. This churning can damage online game's profit and longevity of service if game operators cannot detect this kind of events in time. In this paper, we propose a new technique of PNG image conversion based churn prediction to improve the efficiency of data analysis for the first. By using this log compression technique, we can reduce the size of log files by 52,849 times smaller and increase the analysis speed without features analysis. Second, we apply data mining technique to predict user's churn with a real dataset from Blade & Soul developed by NCSoft. As a result, we can identify potential churners with a high accuracy of 97%.

• Journal of Convergence Society for SMB
• /
• v.5 no.2
• /
• pp.1-6
• /
• 2015

Small and medium-sized companies lack countermeasures to secure the safety of a information system. In this circumstance, they have difficulties regarding the damage to their images and legal losses, when the information is leaked. This paper examines the information leakage of the system and hacking methods including APT attacks. Especially, APT attack, Advanced Persistent Threats, means that a hacker sneaks into a target and has a latency period of time and skims all the information related to the target, and acts in the backstage and neutralize the security services without leaving traces. Because he attacks the target covering up his traces not to reveal them, the victim remains unnoticed, which increases the damage. This study examines attack methods and the process of them and seeks a countermeasure.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.1-9
• /
• 2015

Recently, with smart device proliferation and providing the various services using this, they have interested in mobile and Smart TV security. Smartphone users are enjoying various service, such as cloud, game, banking. But today's mobile security solutions and Study of Smart TV Security simply stays at the level of malicious code detection, mobile device management, security system itself. Accordingly, there is a need for technology for preventing hacking and leakage of sensitive information, such as certificates, legal documents, individual credit card number. To solve this problem, a variety of security technologies(mobile virtualization, ARM TrustZone, GlobalPlatform, MDM) in mobile devices have been studied. In this paper, we propose an efficient method to implement security technology based on TYPE-I virtualization using ARM TrustZone technology.