• Journal of the Korea Society of Computer and Information
• /
• v.12 no.5
• /
• pp.145-154
• /
• 2007

Analyzed about a matter and requirements to intimidate security of ubiquitous and home network threatening various security for personal information protection in ubiquitous home networks at this paper, and studied. Got authentication procedures and verification procedures acid user approach to be reasonable through designs to the home security gateway which strengthened a security function in the outsides, and strengthened protection of a home network. Also, execute a DoS. DDoS, IP Spoofing attack protective at home network security gateways proved, and security regarding against the Hacker's attack was performed, and confirmed. Strengthen appliances and security regarding a user, and confirm a defense regarding an external attack and present a home network security model of this paper to the plans that can strengthen personal information protection in ubiquitous home networks in ubiquitous home networks through experiment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4909-4926
• /
• 2020

Cyberattacks penetrate the server and perform various malicious acts such as stealing confidential information, destroying systems, and exposing personal information. To achieve this, attackers perform various malicious actions by infecting endpoints and accessing the internal network. However, the current countermeasures are only anti-viruses that operate in a signature or pattern manner, allowing initial unknown attacks. Endpoint Detection and Response (EDR) technology is focused on providing visibility, and strong countermeasures are lacking. If you fail to respond to the initial attack, it is difficult to respond additionally because malicious behavior like Advanced Persistent Threat (APT) attack does not occur immediately, but occurs over a long period of time. In this paper, we propose a technique that detects an unknown attack using an event log without prior knowledge, although the initial response failed with anti-virus. The proposed technology uses a combination of AutoEncoder and 1D CNN (1-Dimention Convolutional Neural Network) based on semi-supervised learning. The experiment trained a dataset collected over a month in a real-world commercial endpoint environment, and tested the data collected over the next month. As a result of the experiment, 37 unknown attacks were detected in the event log collected for one month in the actual commercial endpoint environment, and 26 of them were verified as malicious through VirusTotal (VT). In the future, it is expected that the proposed model will be applied to EDR technology to form a secure endpoint environment and reduce time and labor costs to effectively detect unknown attacks.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.111-119
• /
• 2023

Mobile Ad-hoc Network (MANET) is an infrastructure-less network that can configure itself without any centralized management. The topology of MANET changes dynamically which makes it open for new nodes to join it easily. The openness area of MANET makes it very vulnerable to different types of attacks. One of the most dangerous attacks is the Resource Consumption Attack (RCA). In this type of attack, the attacker consumes the normal node energy by flooding it with bogus packets. Routing in MANET is susceptible to RCA and this is a crucial issue that deserves to be studied and solved. Therefore, the main objective of this paper is to study the impact of RCA on two routing protocols namely, Ad hoc On-Demand Distance Vector (AODV) and Dynamic Source Routing (DSR); as a try to find the most resistant routing protocol to such attack. The contribution of this paper is a new RCA model (RCAM) which applies RCA on the two chosen routing protocols using the NS-2 simulator.

• Journal of Platform Technology
• /
• v.11 no.1
• /
• pp.72-84
• /
• 2023

With the rise of the Internet of Things, the security of such lightweight computing environments has become a hot topic. Lightweight block ciphers that can provide efficient performance and security by having a relatively simpler structure and smaller key and block sizes are drawing attention. Due to these characteristics, they can become a target for new attack techniques. One of the new cryptanalytic attacks that have been attracting interest is Neural cryptanalysis, which is a cryptanalytic technique based on neural networks. It showed interesting results with better results than the conventional cryptanalysis method without a great amount of time and cryptographic knowledge. The first work that showed good results was carried out by Aron Gohr in CRYPTO'19, the attack was conducted on the lightweight block cipher SPECK-/32/64 and showed better results than conventional differential cryptanalysis. In this paper, we first apply the Differential Neural Distinguisher proposed by Aron Gohr to the block ciphers HIGHT and GOST to test the applicability of the attack to ciphers with different structures. The performance of the Differential Neural Distinguisher is then analyzed by replacing the neural network attack model with five different models (Multi-Layer Perceptron, AlexNet, ResNext, SE-ResNet, SE-ResNext). We then propose a Related-key Neural Distinguisher and apply it to the SPECK-/32/64, HIGHT, and GOST block ciphers. The proposed Related-key Neural Distinguisher was constructed using the relationship between keys, and this made it possible to distinguish more rounds than the differential distinguisher.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.669-677
• /
• 2020

As the number of Internet users exploded, attacks on the web increased. In addition, the attack patterns have been diversified to bypass existing defense techniques. Traditional web firewalls are difficult to detect attacks of unknown patterns.Therefore, the method of detecting abnormal behavior by artificial intelligence has been studied as an alternative. Specifically, attempts have been made to apply natural language processing techniques because the type of script or query being exploited consists of text. However, because there are many unknown words in scripts and queries, natural language processing requires a different approach. In this paper, we propose a new classification model which uses byte pair encoding (BPE) technology to learn the embedding vector, that is often used for web attack payloads, and uses an attention mechanism-based Bi-GRU neural network to extract a set of tokens that learn their order and importance. For major web attacks such as SQL injection, cross-site scripting, and command injection attacks, the accuracy of the proposed classification method is about 0.9990 and its accuracy outperforms the model suggested in the previous study.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.5
• /
• pp.769-780
• /
• 2014

In general, internet users need to remember several IDs and passwords when they use diverse web sites. From an effective management perspective, SSO system was suggested to reduce user inconvenience. Kerberos authentication, which uses centralized system management, is a typical example of a broker-based SSO authentication model. However, further research is required, because the existing Kerberos authentication system has security vulnerability problems of password and replay attacks. In SSO authentication systems, a major security vulnerability is the replay attack. When user credentials are seized by attackers, an authorized session can be obtained through a replay attack. In this paper, an improved SSO authentication model based on the broker-based model and a secure lightweight SSO mechanism against credential replay attack is proposed.

• International Journal of Computer Science & Network Security
• /
• v.24 no.10
• /
• pp.1-16
• /
• 2024

Due to its complexity and high diagnosis and treatment costs, heart attack (HA) is the top cause of death globally. Heart failure's widespread effect and high morbidity and death rates make accurate and fast prognosis and diagnosis crucial. Due to the complexity of medical data, early and accurate prediction of HA is difficult. Healthcare providers must evaluate data quickly and accurately to intervene. This novel hybrid approach predicts HA using Long Short-Term Memory (LSTM) networks, Deep belief networks (DBNs) with attention mechanism, and robust data mining to fill this essential gap. HA is predicted using Kaggle, PhysioNet, and UCI datasets. Wearable sensor data, ECG signals, and demographic and clinical data provide a solid analytical base. To maintain consistency, ECG signals are normalized and segmented after thorough cleaning to remove missing values and noise. Feature extraction employs complex approaches like Principal Component Analysis (PCA) and Autoencoders to pick time-domain (MNN, SDNN, RMSSD, PNN50) and frequency-domain (PSD at VLF, LF, HF bands) characteristics. The hybrid model architecture uses LSTM networks for sequence learning and DBNs for feature representation and selection to create a robust and comprehensive prediction model. Accuracy, precision, recall, F1-score, and ROC-AUC are measured after cross-entropy loss and SGD optimization. The LSTM-DBN model outperforms predictive methods in accuracy, sensitivity, and specificity. The findings show that several data sources and powerful algorithms can improve heart attack predictions. The proposed architecture performed well on many datasets, with an accuracy rate of 96.00%, sensitivity of 98%, AUC of 0.98, and F1-score of 0.97. High performance proves this system's dependability. Moreover, the proposed approach is outperformed compared to state-of-the-art systems.

• Wind and Structures
• /
• v.22 no.2
• /
• pp.253-272
• /
• 2016

The paper concerns with the method and results of wind tunnel investigations of the Strouhal number (St) of a stationary iced cable model of cable-supported bridges with respect to different angles of wind attack. The investigations were conducted in the Climatic Wind Tunnel Laboratory of the Czech Academy of Sciences in $Tel{\check{c}}$. The methodology leading to the experimental icing of the inclined cable model was prepared in a climatic section of the laboratory. The shape of the ice on the cable was registered by a photogrammetry method. A section of an iced cable model with a smaller scale was reproduced with a 3D printing procedure for subsequent aerodynamic investigations. The St values were determined within the range of the Reynolds number (Re) between $2.4{\cdot}10^4$ and $16.5{\cdot}10^4$, based on the dominant vortex shedding frequencies measured in the wake of the model. The model was oriented at three principal angles of wind attack for each of selected Re values. The flow regimes were distinguished for each model configuration. In order to recognize the tunnel blockage effect the St of a circular smooth cylinder was also tested. Good agreement with the reported values in the subcritical Re range of a circular cylinder was obtained. The knowledge of the flow regimes of the airflow around an iced cable and the associated St values could constitute a basis to formulate a mathematical description of the vortex-induced force acting on the iced cable of a cable-supported bridge and could allow predicting the cable response due to the vortex excitation phenomenon.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.6
• /
• pp.1383-1392
• /
• 2019

Adversarial attack, which geneartes adversarial data to make target model misclassify the input data, is able to confuse real life applications of classification models and cause severe damage to the classification system. An Black-box adversarial attack learns a substitute model, which have similar decision boundary to the target model, and then generates adversarial data with the substitute model. Jacobian-based data augmentation is used to synthesize the training data to learn substitutes, but has a drawback that the data synthesized by the augmentation get distorted more and more as the training loop proceeds. We suggest data augmentation with 'decay factor' to alleviate this problem. The result shows that attack success rate of our method is higher(around 8.5%) than the existing method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.589-598
• /
• 2019

The amount of digital data a is explosively growing, and these data have large potential values. Countries and companies are creating various added values from vast amounts of data, and are making a lot of investments in data analysis techniques. The privacy problem that occurs in data analysis is a major factor that hinders data utilization. Recently, as privacy violation attacks on neural network models have been proposed. researches on artificial neural network technology that preserves privacy is required. Therefore, various privacy preserving artificial neural network technologies have been studied in the field of differential privacy that ensures strict privacy. However, there are problems that the balance between the accuracy of the neural network model and the privacy budget is not appropriate. In this paper, we study differential privacy techniques that preserve the performance of a model within a given privacy budget and is resistant to model inversion attacks. Also, we analyze the resistance of model inversion attack according to privacy preservation strength.