• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.3
• /
• pp.49-57
• /
• 2010

We extended a general attack tree to apply cyber attack model for network vulnerability analysis. We defined an extended cyber attack tree (E-CAT) which extends the general attack tree by associating each node of the tree with a transition of attack that could have contributed to the cyber attack. The E-CAT resolved the limitation that a general attack tree can not express complex and sophisticate attacks. Firstly, the Boolean expression can simply express attack scenario with symbols and codes. Secondary, An Attack Generation Probability is used to select attack method in an attack tree. A CONDITION-composition can express new and modified attack transition which a aeneral attack tree can not express. The E-CAT is possible to have attack's flexibility and improve attack success rate when it is applied to cyber attack model.

• 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.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1227-1236
• /
• 2021

Adversarial attack, one of the attacks on deep learning classification model, is attack that add indistinguishable perturbations to input data and cause deep learning classification model to misclassify the input data. There are various adversarial attack algorithms. Accordingly, many studies have been conducted to detect adversarial attack but few studies have been conducted to classify what adversarial attack algorithms to generate adversarial input. if adversarial attacks can be classified, more robust deep learning classification model can be established by analyzing differences between attacks. In this paper, we proposed a model that detects and classifies adversarial attacks by constructing a random forest classification model with input features extracted from a target deep learning model. In feature extraction, feature is extracted from a output value of hidden layer based on class predicted by the target deep learning model. Through Experiments the model proposed has shown 3.02% accuracy on clean data, 0.80% accuracy on adversarial data higher than the result of pre-existing studies and classify new adversarial attack that was not classified in pre-existing studies.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.6
• /
• pp.1081-1090
• /
• 2022

The face recognition model is used for identity recognition of smartphones, providing convenience to many users. As a result, the security review of the DNN model is becoming important, with adversarial attacks present as a well-known vulnerability of the DNN model. Adversarial attacks have evolved to decision-based attack techniques that use only the recognition results of deep learning models to perform attacks. However, existing decision-based attack technique[14] have a problem that requires a large number of queries when generating adversarial examples. In particular, it takes a large number of queries to approximate the gradient. Therefore, in this paper, we propose a method of generating adversarial examples using orthogonal space sampling and dimensionality reduction sampling to avoid wasting queries that are consumed to approximate the gradient of existing decision-based attack technique[14]. Experiments show that our method can reduce the perturbation size of adversarial examples by about 2.4 compared to existing attack technique[14] and increase the attack success rate by 14% compared to existing attack technique[14]. Experimental results demonstrate that the adversarial example generation method proposed in this paper has superior attack performance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.4
• /
• pp.458-466
• /
• 2012

We have developed a weapon effectiveness evaluation model for top-attack smart munitions(WEEM/TASM), which is a many on many Monte Carlo Model evaluating the effectiveness of top-attack smart munitions against armoured ground vehicles. In this model the battle is reduced to a one-sided battle situation in that the target vehicles are regarded as being stationary and passive. It can simulate the whole attack process of smart munitions from firing artillery dispenser to sensing and hitting processes after dispense. It can also calculate the probability of kill of each target and the numbers of rounds required to fulfill the degree of damage in statistical manners. In this paper, we describe the basis for our design concepts reflected in the model to simulate the weapon effectiveness of top-attack smart munitions and provide simulation results for an example case.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.660-663
• /
• 2003

The advanced computer network technology enables connectivity of computers through an open network environment. There has been growing numbers of security threat to the networks. Therefore, it requires intrusion detection and prevention technologies. In this paper, we propose a network based intrusion detection model using Fuzzy Cognitive Maps(FCM) that can detect intrusion by the Denial of Service(DoS) attack detection method adopting the packet analyses. A DoS attack appears in the form of the Probe and Syn Flooding attack which is a typical example. The Sp flooding Preventer using Fuzzy cognitive maps(SPuF) model captures and analyzes the packet information to detect Syn flooding attack. Using the result of analysis of decision module, which utilized FCM, the decision module measures the degree of danger of the DoS and trains the response module to deal with attacks. The result of simulating the "KDD ′99 Competition Data Set" in the SPuF model shows that the Probe detection rates were over 97 percentages.

• The Journal of the Korea Contents Association
• /
• v.5 no.6
• /
• pp.172-177
• /
• 2005

Hit judgement is essential factor in design for battle-style MMORPG game system and sets foundation for other game systems. Hit judgement model consists of attack power and attack rate. The former contains minimum, maximum, and critical attack, the latter has miss, hit, and critical blow rate. Random function generates one value of attack rate and consequently the damage is calculated. In this article, we propose hit judgement model which Is widely acceptable for generic MMORPG and describe the effort of applying the proposed model to Travia Online in detail.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2731-2749
• /
• 2012

Sybil attack has been proved effective in mitigating the P2P botnet, but the impacts of some important parameters were not studied, and no model to estimate the effectiveness was proposed. In this paper, taking Kademlia-based botnets as the example, the model which has the upper and lower bound to estimate the mitigating performance of the Sybil attack is proposed. Through simulation, how three important factors affect the performance of the Sybil attack is analyzed, which is proved consistent with the model. The simulation results not only confirm that for P2P botnets in large scale, the Sybil attack is an effective countermeasure, but also imply that the model can give suggestions for the deployment of Sybil nodes to get the ideal performance in mitigating the P2P botnet.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.5
• /
• pp.1021-1030
• /
• 2021

This paper proposes S-CAFG(Stage-based Cyber Attack Flow Graph), a model for effectively describing training scenarios that simulate modern complex cyber attacks. On top of existing graph and tree models, we add a stage node to model more complex scenarios. In order to evaluate the proposed model, we create a complicated scenario and compare how the previous models and S-CAFG express the scenario. As a result, we confirm that S-CAFG can effectively describe various attack scenarios such as simultaneous attacks, additional attacks, and bypass path selection.

• 한국전산유체공학회:학술대회논문집
• /
• 2007.04a
• /
• pp.45-49
• /
• 2007

Asymmetric force and vibration caused by separation flow at high angle of attack affect the stability of supersonic missile. As a preliminary study we verified the effect of turbulence model through general 3-D slender body for the supersonic flow at high angle of attack. ${\kappa}-{\omega}$ Wilcox model, ${\kappa}-{\omega}$ Wilcox-Durbin+ model, ${\kappa}-{\omega}$ shear-stress transport model, and Spalart-Allmaras one equation model are used. Grid sensitivity test was performed with three different grid system. results show that all models are in good agreement with the experimental data.