• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.201-207
• /
• 2024

Voice is a critical element of human communication, and the development of speech recognition models is one of the significant achievements in artificial intelligence, which has recently been applied in various aspects of human life. The application of speech recognition models in the military field is also inevitable. However, before artificial intelligence models can be applied in the military, it is necessary to research their vulnerabilities. In this study, we evaluates the military applicability of the multilingual speech recognition model "Whisper" by examining its vulnerabilities to battlefield noise, white noise, and adversarial attacks. In experiments involving battlefield noise, Whisper showed significant performance degradation with an average Character Error Rate (CER) of 72.4%, indicating difficulties in military applications. In experiments with white noise, Whisper was robust to low-intensity noise but showed performance degradation under high-intensity noise. Adversarial attack experiments revealed vulnerabilities at specific epsilon values. Therefore, the Whisper model requires improvements through fine-tuning, adversarial training, and other methods.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.1
• /
• pp.90-98
• /
• 2022

On February 12, 2019, the U.S. Department of Defense newly established and announced the "Defense AI Strategy" to accelerate the use of artificial intelligence (AI) technology for military purposes. As China and Russia invested heavily in AI for military purposes, the U.S. was concerned that it could eventually lose its advantage in AI technology to China and Russia. In response, China and Russia, which are hostile countries, and especially China, are speeding up the development of new military theories related to the overall construction and operation of the Chinese military based on AI. With the rapid development of AI technology, major advanced countries such as the U.S. and China are actively researching the application of AI technology, but most existing studies do not address the special topic of defense. Fortunately, the "Future Defense 2030 Technology Strategy" classified AI technology fields from a defense perspective and analyzed advanced overseas cases to present a roadmap in detail, but it has limitations in comparing private technology-oriented benchmarking and AI technology's maturity level. Therefore, this study tried to overcome the limitations of the "Future Defense 2030 Technology Strategy" by comparing and analyzing Chinese and U.S. military research cases and evaluating the maturity level of military use of AI technology, not AI technology itself.

• Journal of the Korean Geographical Society
• /
• v.44 no.6
• /
• pp.761-778
• /
• 2009

This study investigates and proves the historical facts about the confidential land survey on Korean peninsula made by Japanese intelligence officers at the end of Chosun Dynasty. Under the command of general staff office of Japanese army, the military officers produced several maps through road map measurements and visual measurements. Although previous literature indicated road map measurements on Korea were originally implemented from 1885, this study confirms that road map measurements were initiated in 1882 by a lieutenant Isobayashi. Reflecting secret map making procedures, the individual military intelligence officers had specialized roles for swift information collection and map production.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.3
• /
• pp.300-310
• /
• 2022

A vast amount of labeled data is required for deep neural network training. A typical strategy to improve the performance of a neural network given a training data set is to use data augmentation technique. The goal of this work is to offer a novel image augmentation method for improving object detection accuracy. An object in an image is removed, and a similar object from the training data set is placed in its area. An in-painting algorithm fills the space that is eliminated but not filled by a similar object. Our technique shows at most 2.32 percent improvements on mAP in our testing on a military vehicle dataset using the YOLOv4 object detector.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.4
• /
• pp.396-407
• /
• 2015

The literature about intelligence assets allocation focused on mainly single or partial assets such as TOD and GSR. Thus, it is limited in application to the actual environment of operating various assets. In addition, field units have generally vulnerabilities because of depending on qualitative analysis. Therefore, we need a methodology to ensure the validity and reliability of intelligence asset allocation. In this study, detection probability was generated using digital geospatial data in MGIS (Military Geographic Information System) and simulation logic of BCTP (Battle Commander Training Programs) in the R.O.K army. Then, the optimal allocation mathematical model applied concept of simultaneous integrated management, which was developed based on the partial set covering model. Also, the proposed GA (Genetic Algorithm) provided superior results compared to the mathematical model. Consequently, this study will support effectively decision making by the commander by offering the best alternatives for optimal allocation within a reasonable time.

• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.205-210
• /
• 2022

Drones, which have rapidly grown along with the 4th industrial revolution, spread over industries and also widely used for military purposes. In recent wars in Europe, drones are being evaluated as a game changer on the battlefield, and their importance for military use is being highlighted. The Republic of Korea Army also planned drone-bot systems including various drones suitable for echelons and missions of the military as future defense forces. The keyword of these drone-bot systems is autonomy by artificial intelligence. In addition, common use of operating platforms is required for the rapid development of various types of drones. In this paper, we propose software framework that applies diverse artificial intelligence technologies such as multi-agent system, cognitive architecture and knowledge-based context reasoning for mission autonomy and common use of military drones.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.12-19
• /
• 2022

Artificial intelligence is driving the Fourth Industrial Revolution and is in the spotlight as a general-purpose technology. As the data collection from the battlefield increases rapidly, the need to us artificial intelligence is increasing in the military, but it is still in its early stages. In order to identify maritime targets, Republic of Korea navy acquires images by ISAR(Inverse Synthetic Aperture Radar) of maritime patrol aircraft, and humans make out them. The radar image is displayed by synthesizing signals reflected from the target after radiating radar waves. In addition, day/night and all-weather observations are possible. In this study, an artificial intelligence is used to identify maritime targets based on radar images. Data of radar images of 24 maritime targets in Republic of Korea and North Korea acquired by ISAR were pre-processed, and an artificial intelligence algorithm(ResNet-50) was applied. The accuracy of maritime targets identification showed about 99%. Out of the 81 warship types, 75 types took less than 5 seconds, and 6 types took 15 to 163 seconds.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.3
• /
• pp.323-328
• /
• 2014

Recently, there has been demand for the convergence of IT (Information and communication Technologies, ICT) with defense, as has already been achieved in civilian fields such as healthcare and construction. It is expected that completely new and common requirements would emerge from the civilian and military domains and that the shape of war field would change rapidly. Many military scientists forecast that future wars would be network-centric and be based on C4I(Command, Control, Communication & Computer, Intelligence), ISR(Intelligence, Surveillance & Reconnaissance), and PGM(Precision Guided Munitions). For realizing the smart defense concept, IT should act as a baseline technology even for simulating a real combat field using virtual reality. In this paper, we propose the concept of IT-based smart defense with a focus on accurate detection in real and cyber wars, effective data communication, automated and unmanned operation, and modeling and simulation.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.216-222
• /
• 2021

COVID-19 pandemic brings attentions to the nonmilitary and transnational non-traditonal security threats, as the scales of such damage by these threats are beyond expectation. The Republic of Korea Army tries to forecast non-traditional security threat which may be occurred in Korean peninsula by using collective intelligence platform. In coming years, climate change, social changes and technology development caused by the 4th industrial revolution will diversify non-traditional security threat. Considering urbanization, internet distribution rate, and geopolitical location where atmosphere from continent and ocean meet, Korea would may face the most lethal ones compared to those of other countries may face. Therefore, to predict such threats in pangovernment scale using collective intelligence platforms which embrace civil, public, military, industry, academy and research center is the most important than anything.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.5-6
• /
• 2019

본 논문에서는 데이터 기반 정보 고도화를 통해, 사격전술지휘 의사결정체계의 Assisted Decision-Maker인 AI 부전포대장을 구현하는 방법론을 제시한다. 전포대장은 지휘결심의 말단에 있는 지휘관으로서, 최종적인 의사결정자이다. 이들의 지휘결심이 보다 견고하고 신속하게 이루어지도록 하는 것이 전쟁 승패에 매우 중요한 요소이다. 화력체계를 언급하는 경우 JMEM 탄약효과가 자주 언급되고 한국형 구축 사업이 아직 진행 중이기도 하지만, 완료되더라도 임의의 지형과 전술상황 각각에 대한 유용성까지를 입증하는 데에는 또 다른 기간과 노력이 요구된다. 본고에서는 AI 플랫폼 구축의 실제 사례가 전무한 상황에서 AI 부전포대장 구축을 위해 필요한 연구의 범위와 그 대상을 살펴보고, 지능형 사격지휘체계의 구축 방안을 제안한다.