• International journal of advanced smart convergence
• /
• v.11 no.4
• /
• pp.10-19
• /
• 2022

AI-based Network Intrusion Detection Systems (AI-NIDS) detect network attacks using machine learning and deep learning models. Recently, unsupervised AI-NIDS methods are getting more attention since there is no need for labeling, which is crucial for building practical NIDS systems. This paper aims to test the impact of designing autoencoder models that can be applied to unsupervised an AI-NIDS in real network systems. We collected security events of legacy network security system and carried out an experiment. We report the results and discuss the findings.

• Journal of Digital Convergence
• /
• v.18 no.5
• /
• pp.17-23
• /
• 2020

With the advancement of AI technology, legal status and regulation issues for AI robots, and the necessity of a robot registration system are emerging. Since the shape and activity area of AI robots will no longer be limited to hardware in one country, the definition and regulation of AI robots should be expanded to a comprehensive concept including software, and information about them should be securely managed and shared by governments around the world. From this perspective, we extend 'AI robot' to the concept of Juridical AI encompassing hardware and software, and propose a method to operate the Juridical AI registration system using a permissioned blockchain called Juridical AI Chain. Since blockchain is an internationally distributed database, operating such AI registration system based on the blockchain will be a way to effectively cope with the global problems caused by the commercialization of AI robots.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1053-1054
• /
• 2023

본 연구는 이기종 기체 센서를 활용하여 식품의 부패 및 발효 정도를 측정하기 위한 AI 기반 식품 품질 관리용 전자코에 관한 내용이다. 정확한 부패 및 발효 정도 측정을 위해 신호 처리 및 분석 기술을 활용하며, 로지스틱 분석 및 회귀 분석을 통해 결과를 도출하고자 한다. 이는 인간의 후각으로 정확하게 맡기 힘든 냄새를 측정함으로써 식중독 사고의 방지 및 식품의 생산/보관/운송을 효율적으로 관리할 수 있다. 또한, 본 연구 결과를 바탕으로 환경, 농업, 의료 등 다양한 분야에서의 적용 가능성을 기대할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.838-839
• /
• 2023

배달량 확산과 자율 주행 로봇의 실내외 주행이 가능해지면서 로봇을 활용할 주문 및 배달 서비스가 활발해지고 있다. 따라서 기존의 자율 주행 배달 로봇의 문제점을 개선하여 보다 나은 배달 서비스를 제공하고자 자율 주행 배달 로봇을 연구하였다. 배달 로봇에 AI를 적용하여 장애물 탐지, 최적코스 탐색을 통해 목적지까지 최적 경로로 이동하며, 배달 물품 안전까지 보장한다.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.245-251
• /
• 2021

This work aims to focus on the current features and characteristics of Human Element and Artificial intelligence (AI), ask some questions about future information security, and whether we can avoid human errors by improving machine learning and AI or invest in human knowledge more and work them both together in the best way possible? This work represents several related research results on human behavior towards information security, specified with elements and factors like knowledge and attitude, and how much are they invested for ISA (information security awareness), then presenting some of the latest studies on AI and their contributions to further improvements, making the field more securely advanced, we aim to open a new type of thinking in the cybersecurity field and we wish our suggestions of utilizing each point of strengths in both human attributions in software security and the existence of a well-built AI are going to make better future software security.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1466-1488
• /
• 2022

Recently, the importance and necessity of artificial intelligence (AI), especially machine learning, has been emphasized. In fact, studies are actively underway to solve complex and challenging problems through the use of AI systems, such as intelligent CCTVs, intelligent AI security systems, and AI surgical robots. Information security that involves analysis and response to security vulnerabilities of software is no exception to this and is recognized as one of the fields wherein significant results are expected when AI is applied. This is because the frequency of malware incidents is gradually increasing, and the available security technologies are limited with regard to the use of software security experts or source code analysis tools. We conducted a study on MalDC, a technique that converts malware into images using machine learning, MalDC showed good performance and was able to analyze and classify different types of malware. MalDC applies a preprocessing step to minimize the noise generated in the image conversion process and employs an image augmentation technique to reinforce the insufficient dataset, thus improving the accuracy of the malware classification. To verify the feasibility of our method, we tested the malware classification technique used by MalDC on a dataset provided by Microsoft and malware data collected by the Korea Internet & Security Agency (KISA). Consequently, an accuracy of 97% was achieved.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.629-632
• /
• 2020

현대사회는 4차 산업혁명 시대가 도래하면서 초연결, 초지능, 초융합 사회로 변화되고 있다. 최근 교육부는 많은 변화가 요구되고 있는 교육분야, 교육정책 방안으로 SW(소프트웨어)교육에 AI(인공지능) 교육까지 추가되야 한다고 제안하고 2024년까지 첨단 기술을 활용한 지능형 과학실을 구축한다고 밝혔다. 이에 본 논문에서는 정부의 교육정책 방안이 원활하게 진행될 수 있고 융합 교육 분야에서 활용될 수 있는 "미래 지능형 과학실 활용을 위한 화학원소기호 이미지 기계학습 AI·SW교육 프로그램"을 제안하고자 한다.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.217-225
• /
• 2024

To foster the core talents of the future, the development of diverse and substantial SW·AI education programs is required, and a systematic system that can assist public education in SW and AI must be established. In this study, we develop and combine SW·AI education modules to construct a SW and AI education program applicable to public education. We also establish a systematic education system and provide sustainable SW·AI education to elementary, middle, and high school students through 'Job's Garage Camp' based on various sharing platforms. By creating a sustainable follow-up educational environment, students are encouraged to continue their self-directed learning of SW and AI. As a result of conducting a pre-post survey of students participating in the 'Job's Garage Camp', the post-survey values improved compared to the pre-survey values in all areas of 'interest', 'understanding and confidence', and 'career aspirations'. Based on these results, it can be confirmed that students had a universal positive perception and influence on SW and AI. Therefore, if the operation case of 'Job's Garage Camp' is improved and expanded, it can be presented as a standard model applicable to other SW and AI education programs in the future.

• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.32-42
• /
• 2021

The rapid growth of deep-learning applications has invoked the R&D of artificial intelligence (AI) processors. A dedicated software framework such as a compiler and runtime APIs is required to achieve maximum processor performance. There are various compilers and frameworks for AI training and inference. In this study, we present the features and characteristics of AI compilers, training frameworks, and inference engines. In addition, we focus on the internals of compiler frameworks, which are based on either basic linear algebra subprograms or intermediate representation. For an in-depth insight, we present the compiler infrastructure, internal components, and operation flow of ETRI's "AI-Ware." The software framework's significant role is evidenced from the optimized neural processing unit code produced by the compiler after various optimization passes, such as scheduling, architecture-considering optimization, schedule selection, and power optimization. We conclude the study with thoughts about the future of state-of-the-art AI compilers.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.277-278
• /
• 2024

일반적으로 한국인은 식사를 위해 음식 메뉴를 고를 때 쉽게 결정하지 못하는 비율이 50% 이상으로 높다고 알려져 있다. 이러한 단순 고민 해결을 위해 다양한 음식이나 맛집을 추천해 주는 모바일 앱이나 서비스가 존재한다. 그러나 이들은 사용자가 평소 많이 검색했던 음식이나 맛집들을 위주로 찾아주거나, 랜덤으로 지정된 카테고리 내의 음식들 중 하나를 추천해주는 방식, 혹은 사용자 리뷰 점수가 높은 음식점을 우선적으로 추천해 주는 방식 등을 사용하고 있다. 따라서 기존의 추천 방식은 음식을 추천에 있어 사용자의 의도나 실질적인 연관성이 매우 낮고 평소 먹던 음식의 종류를 크게 벗어나지 않는 경우가 많아 음식 추천이라는 본래의 취지와는 멀어진다. 본 논문에서는 음식 메뉴를 선정하는데 있어 실질적인 영향을 주는 환경 요소인 계절, 기후 등의 날씨 정보를 기반으로 생성형 AI를 통해 적절한 음식을 추천하고 해당 음식을 판매하는 음식점과 그 위치를 알려주는 앱을 개발한다. 개발하는 앱은 바쁜 직장인들이나 매 끼니를 고민하는 학생 등의 메뉴 고민을 해결하는데 도움을 줄 수 있으며, 각종 배달 서비스 앱의 음식 추천 기능의 고도화에 활용될 수 있다.