• Journal of Multimedia Information System
• /
• 제9권1호
• /
• pp.11-20
• /
• 2022

In this paper, we have recently created self-driving cars and self-parking systems in human-friendly cars that can provide high safety and high convenience functions by recognizing the internal and external situations of automobiles in real time by incorporating next-generation electronics, information communication, and function control technologies. And with the development of connected cars, the ITS (Intelligent Transportation Systems) market is expected to grow rapidly. Intelligent Transportation System (ITS) is an intelligent transportation system that incorporates technologies such as electronics, information, communication, and control into the transportation system, and aims to implement a next-generation transportation system suitable for the information society. By combining the technologies of connected cars and Internet of Things with software features and operating systems, future cars will serve as a service platform to connect the surrounding infrastructure on their own. This study creates a research methodology based on the Enhanced Security Model in Self-Driving Cars model. As for the types of attacks, Availability Attack, Man in the Middle Attack, Imperial Password Use, and Use Inclusive Access Control attack defense methodology are used. Along with the commercialization of 5G, various service models using advanced technologies such as autonomous vehicles, traffic information sharing systems using IoT, and AI-based mobility services are also appearing, and the growth of smart transportation is accelerating. Therefore, research was conducted to defend against hacking based on vulnerabilities of smart cars based on artificial intelligence blockchain.

• 한국안전학회지
• /
• 제37권4호
• /
• pp.1-10
• /
• 2022

The purposes of this study were to suggest 1) a future direction for Korea's machine tool industry and 2) how to secure the safety and reliability of emerging intelligent or automated machine tooling. The study concludes that, overseas, the machine tool industry is growing again while promoting innovation by converging with ICT. Accordingly, Korea also promotes ICT innovation to advance the machine tool industry, which is at the core of the national economy. As a result, unlike in the past, the frequency of serious injuries like entrapment accidents has recently decreased, while the proportion of collision accidents has increased. In addition, a new type of accident has become possible. Since ICT is network-based, the distinction between work and rest can become ambiguous; there is a risk of hacking, working hours and places are flexible and there are risk factors for diseases like chronic fatigue due to overload of specific personnel. As robots and automation are introduced, there is also a high probability of problems caused by physical and psychological burdens on system operators and resulting fatigue.

• 정보보호학회논문지
• /
• 제31권6호
• /
• pp.1279-1290
• /
• 2021

차량 기술이 성장하면서 운전자의 개입이 필요 없는 자율주행까지 발전하였고, 이에 따라 차량 내부 네트워크인 CAN 보안도 중요해졌다. CAN은 해킹 공격에 취약점을 보이는데, 이러한 공격을 탐지하기 위해 기계학습 기반 IDS가 도입된다. 하지만 기계학습은 높은 정확도에도 불구하고 적대적 예제에 취약한 모습을 보여주었다. 본 논문에서는 IDS를 회피할 수 있도록 feature에 잡음을 추가하고 또한 실제 차량의 physical attack을 위한 feature 선택 및 패킷화를 진행하여 IDS를 회피하고 실제 차량에도 공격할 수 있도록 적대적 CAN frame 생성방법을 제안한다. 모든 feature 변조 실험부터 feature 선택 후 변조 실험, 패킷화 이후 전처리하여 IDS 회피실험을 진행하여 생성한 적대적 CAN frame이 IDS를 얼마나 회피하는지 확인한다.

• 한국BIM학회 논문집
• /
• 제13권3호
• /
• pp.12-20
• /
• 2023

Deep learning-based anomaly detection technology is used in various fields such as computer vision, speech recognition, and natural language processing. In particular, this technology is applied in various fields such as monitoring manufacturing equipment abnormalities, detecting financial fraud, detecting network hacking, and detecting anomalies in medical images. However, in the field of construction and architecture, research on deep learning-based data anomaly detection technology is difficult due to the lack of digitization of domain knowledge due to late digital conversion, lack of learning data, and difficulties in collecting and processing field data in real time. This study acquires necessary data through IoT (Internet of Things) from the viewpoint of monitoring for environmental management of architectural spaces, converts them into a database, learns deep learning, and then supports anomaly patterns using AI (Artificial Infelligence) deep learning-based anomaly detection. We propose an implementation process. The results of this study suggest an effective environmental anomaly pattern detection solution architecture for environmental management of architectural spaces, proving its feasibility. The proposed method enables quick response through real-time data processing and analysis collected from IoT. In order to confirm the effectiveness of the proposed method, performance analysis is performed through prototype implementation to derive the results.

• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.817-837
• /
• 2019

The medical industry is rapidly evolving into a combination of artificial intelligence (AI) and ICT technology, such as mobile health, wireless medical, telemedicine and precision medical care. Medical artificial intelligence can be diagnosed and treated, and autonomous surgical robots can be operated. For smart medical services, data such as medical information and personal medical information are needed. AI is being developed to integrate with companies such as Google, Facebook, IBM and others in the health care field. Telemedicine services are also becoming available. However, security issues of medical information for smart medical industry are becoming important. It can have a devastating impact on life through hacking of medical devices through vulnerable areas. Research on medical information is proceeding on the necessity of privacy and privacy protection. However, there is a lack of research on the practical measures for protecting medical information and the seriousness of security threats. Therefore, in this study, we want to confirm the research trend by collecting data related to medical information in recent 5 years. In this study, smart medical related papers from 2014 to 2018 were collected using smart medical topics, and the medical information papers were rearranged based on this. Research trend analysis uses topic modeling technique for topic information. The result constructs topic network based on relation of topics and grasps main trend through topic.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권6호
• /
• pp.1619-1637
• /
• 2024

In today's highly digitized landscape, securing digital communication is paramount due to threats like hacking, unauthorized data access, and network policy violations. The response to these challenges has been the development of cryptography applications, though many existing techniques face issues of complexity, efficiency, and limitations. Notably, sophisticated intruders can easily discern encrypted data during transmission, casting doubt on overall security. In contrast to encryption, steganography offers the unique advantage of concealing data without easy detection, although it, too, grapples with challenges. The primary hurdles in image steganography revolve around the quality and payload capacity of the cover image, which are persistently compromised. This article introduces a pioneering approach that integrates image steganography and encryption, presenting the BitPatternStego method. This novel technique addresses prevalent issues in image steganography, such as stego-image quality and payload, by concealing secret data within image pixels with identical bit patterns as their characters. Consequently, concerns regarding the quality and payload capacity of steganographic images become obsolete. Moreover, the BitPatternStego method boasts the capability to generate millions of keys for the same secret message, offering a robust and versatile solution to the evolving landscape of digital security challenges.

• 한국전자통신학회논문지
• /
• 제8권12호
• /
• pp.1841-1848
• /
• 2013

본 논문에서는 매우 국한된 사이버공격에만 대응할 수 있는 기존 정형화 탐지패턴 기반의 보안관제를 극복하기 위하여 대규모 네트워크상에서 유출입 되는 이상행위 정보에 대한 종합적 체계적 수집 분석을 통해 실시간 보안관제 정확도 향상 및 관제영역 확대 방안에 대하여 연구하였다. 다크넷 네트워크상에 유입되는 다양한 침해위협 정보들을 수집 저장 분석하기 위한 이상 징후 관측 체계를 구축하고 통계 기반의 해킹동향 분석을 통해 알려진 사이버위협, 알려지지 않은 이상징후 및 고위험 이상행위 정보 분류 체계를 제시하였다. 본 연구에서 제시한 다크넷 트래픽을 활용한 보안관제 체계를 적용할 경우, 전체 침해위협 탐지가 기존 대비 12.6% 증가하였으며, 기존에는 감지할 수 없었던 신종 변종 공격을 120여종 감지하는 것으로 나타났다.

• 디지털산업정보학회논문지
• /
• 제13권4호
• /
• pp.141-151
• /
• 2017

Nowadays, It is undeniable that the threat of network security is growing as time flows due to worldwide development of wire/wireless, various Internet platform and sophisticated hacking techniques. The amount of traffics that Network security solution has to handle is increasing and recently many occurrence of explosive traffic attacks from PulseWave are being observed which has many similar characteristics to New DDos. Medium and small sized firms abroad have developed and distributed Snort and Suricata that are based on open-source Intrusion Detection System(IDS) / Intrusion Prevention System (IPS). The goal of this study is to compare between Windows7 by applying suicata 4.0.0 32bit version and Ubuntu 16.04.3 LTS by applying suicata 4.0.0 version which is an open source Intrusion Detection System / Intrusion Protection System that uses multi threads method. This experiment's environment was set as followed C1100 server model of Dell, Intel Xeon CPU L5520 2.27GHz*2 with 8 cores and 16 threads, 72GB of RAM, Samsung SSD 250GB*4 of HDD which was set on RAID0. According to the result, Suricata in Ubuntu is superior to Suricata in Windows7 in performance and this result indicates that Ubuntu's performance is far advanced than Windows7. This meaningful result is derived because Ubuntu that applied Suricata used multi core CPU and RAM more effectively.

• 정보처리학회논문지C
• /
• 제9C권3호
• /
• pp.359-366
• /
• 2002

인터넷의 발전과 더불어 해킹기법 또한 함께 발전하고 있다. 최근의 검색공격 형태는 한 기관의 네트워크를 대상으로 하기보다는 상위 도메인을 대상으로 대규모적인 공격 형태를 지니고 있다. 실질적으로 대응하기 위해서는 중앙시스템에서 취약점 검색공격을 탐지, 분석하고 조치할 수 있는 시스템이 있어야 한다. 침입시도탐지 관리시스템은 현재 국내 주요기관들에 설치된 다수의 침입시도탐지 시스템들로부터 받은 여러 탐지 정보를 실시간으로 수집 분석하여 효과적으로 이용하는데 유용하다. 대규모 네트워크의 환경에 적절한 구조를 갖으며 보다 고수준의 통합된 분석을 할 수 있는 실시간 침입시도탐지 관리시스템을 개발하였다.

• 산업경영시스템학회지
• /
• 제40권3호
• /
• pp.116-122
• /
• 2017

Advances in information technology, communication and network technology are radically facilitating digital convergences as the integration of human, equipment, and space in the current industry 4.0 era. In industry 4.0 environment, the vast amount of information with networked computing technology can be simultaneously accessible even in limited physical space. Two main benefit points out of these information are the convenience and efficiency in their online transactions either buying things online or selling online. Even though there exist so many benefits that information technology can create for the people doing business over the internet there is a critical problem to be answered. In spite of many such advantages, however, online transactions have many dysfunctions such as personal information leakage, account hacking, and cybercrime. Without preparing the appropriate protection methods or schema people reluctantly use the transaction or would find some other partners with enhanced information security environment. In this paper we suggested a novel selection criteria that can be used to evaluate the reliable means of authentication against the expected risks under on-going IoT based environment. Our selection criteria consists of 4 steps. The first step is services and risk identification step. The second step is evaluation of risk occurrence step. The third step includes the evaluation of the extent of damage. And the final step is the assessment of the level of risk. With the help of the above 4 step-approach people can systematically identify potential risks hiding in the online transactions and effectively avoid by taking appropriate counter actions.