• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.44-53
• /
• 2023

Adversarial attacks have received great attentions for their capacity to distract state-of-the-art neural networks by modifying objects in physical domain. Patch-based attack especially have got much attention for its optimization effectiveness and feasible adaptation to any objects to attack neural network-based object detectors. However, despite their strong attack performance, generated patches are strongly perceptible for humans, violating the fundamental assumption of adversarial examples. In this paper, we propose a camouflaged adversarial patch optimization method using military camouflage assessment metrics for naturalistic patch attacks. We also investigate camouflaged attack loss functions, applications of various camouflaged patches on army tank images, and validate the proposed approach with extensive experiments attacking Yolov5 detection model. Our methods produce more natural and realistic looking camouflaged patches while achieving competitive performance.

• Nano
• /
• v.13 no.11
• /
• pp.1850125.1-1850125.12
• /
• 2018

To reduce the imbalance of impedance matching between the magnetic metal nanowires and free space, $Fe/TiO_2$ core/shell nanowire arrays with different diameters were fabricated in the templates of anodic aluminum oxide membranes by electrodeposition. The influences of the microstructure on the microwave absorption properties of the $Fe/TiO_2/Al_2O_3$ composites were studied by the transmission/reflection waveguide method. It was demonstrated experimentally that both the interfacial polarization and the diameter of the $Fe/TiO_2$ core/shell nanowires have critical effects on the microwave absorption properties. We also investigated the angle dependence of the microwave absorption properties. Due to the interfacial polarization and associated relaxation, the $Fe/TiO_2/Al_2O_3$ composites exhibited optimal microwave absorption properties when microwave propagation direction was accordant with the axis of the nanowires. Finally, we managed to obtain an optimal reflection loss of below -10 dB (90% absorption) over 10.2-14.8 GHz, with a thickness of 3.0 mm and the minimum value of -39.4 dB at 11.7 GHz.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.1
• /
• pp.70-79
• /
• 2009

Currently, the investment on Research and Development(R&D) for defense core technology is continuously increasing to maintain advanced country's R&D level. In accordance with this trend, the national defense R&D investment management system is being more strengthening, and importance of performance evaluation is being emphasized more and more. However, the existing indicators of performance evaluation for defense core technology R&D is limited in efficient management because of the qualitative evaluation items and subjective allocation of points. In this paper, we developed a novel indicator for defense core technology R&D performance evaluation through domestic and foreign related literature and inquiry, brainstorming, and analysis techniques by Stepwise Multiple linear Regression(SMR) and Analytic Hierarchy Process(AHP). And we verified effectiveness of proposed indicators of performance evaluation by comparing with the existing evaluation indicators. Our proposed indicators for performance evaluation will create superiority performance on defense R&D fields.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.1
• /
• pp.106-123
• /
• 2019

Demand for performance analysis is increasing for efficient use of limited budgets such as improving investment efficiency and strategic budget allocation in accordance with the continuous increase demand of R&D budget for developing advanced weapon systems in the future battlefields. In accordance with the Act on the Performance Evaluation and Performance Management of the National R&D Projects established in March 2006, the performance analysis has been conducted for the systematic management and utilization of the R&D project performance. It was recognized as a project to achieve self-defense through strengthening the weapons system development capability, however, efficiency evaluation of Defense R&D projects was not much emphasized. Research on the efficiency analysis of defense R&D projects has been conducted in recent years, but most studies focused on corporate efficiency and productivity of defense companies. In this study, we analyzed the three-stage performance of defence R&D projects based on the logical model using the data envelope analysis(DEA) model. We also analyzed performance analysis from various perspectives through R&D type, technology classification and performance model. This study is expected to help defense department improve defense R&D projects and make decision.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.3
• /
• pp.416-427
• /
• 2024

The wake-homing underwater guided weapon that detects and tracks wake generated during voyage of a surface ship is impossible to avoid with the present acoustic deception torpedo defense system. Therefore, research on bubble-generating wake decoy is necessary to deceive wake-homing underwater guided weapon. Experiments in various environments are required to verify the effective operation method and performance of the wake decoy, but performance verification through underwater experiment is limited. In this paper, we develop a simulator for an torpedo defense system of surface ship, which is applied bubble-generating wake decoy, against acoustic, wake, and hybrid homing underwater guided weapon attack. The simulator includes surface ship model, acoustic decoy(static, mobile) model, bubble-generating wake decoy model, search and motion model of underwater guided weapon and so on. By integrating various models, MATLAB GUI simulator was developed. Through the simulation results for various environmental variables by this simulator, it is judged that effective operation method and performance verification of the bubble-generating wake decoy can be performed.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.5
• /
• pp.619-627
• /
• 2024

As AI technology advances, interest in performing multi-robot autonomous missions for manned-unmanned teaming (MUM-T) is increasing. In order to develop autonomous mission performance technology for multiple robots, simulation technology that reflects the characteristics of real robots and can flexibly apply various missions is needed. Additionally, in order to solve complex non-linear tasks, an API must be provided to apply multi-robot reinforcement learning technology, which is currently under active research. In this study, we propose the campaign model to flexibly simulate the missions of multiple robots. We then discuss the results of developing a simulation environment that can be edited and run and provides a reinforcement learning API including acceleration performance. The proposed simulated control module and simulated environment were verified using an enemy infiltration scenario, and parallel processing performance for efficient reinforcement learning was confirmed through experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.6
• /
• pp.1496-1521
• /
• 2012

Uncertainty is ubiquitous in target tracking wireless sensor networks due to environmental noise, randomness of target mobility and other factors. Sensing results are always unreliable. This paper considers unreliability as it occurs in wireless sensor networks and its impact on target-tracking accuracy. Firstly, we map intersection pairwise sensors' uncertain boundaries, which divides the monitor area into faces. Each face has a unique signature vector. For each target localization, a sampling vector is built after multiple grouping samplings determine whether the RSS (Received Signal Strength) for a pairwise nodes' is ordinal or flipped. A Fault-Tolerant Target-Tracking (FTTT) strategy is proposed, which transforms the tracking problem into a vector matching process that increases the tracking flexibility and accuracy while reducing the influence of in-the-filed factors. In addition, a heuristic matching algorithm is introduced to reduce the computational complexity. The fault tolerance of FTTT is also discussed. An extension of FTTT is then proposed by quantifying the pairwise uncertainty to further enhance robustness. Results show FTTT is more flexible, more robust and more accurate than parallel approaches.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.6
• /
• pp.580-585
• /
• 2022

In this study, the high-temperature dielectric constant of Si₃N₄ ceramics, a representative non-oxide-based radome material, was evaluated and the cause of the dielectric constant change was analyzed in relation to the oxidation behavior. The dielectric constant of Si₃N₄ ceramics was 7.79 at room temperature, and it linearly increased as the temperature increased, showing 8.42 at 1,000 ℃. As results of analyzing the microstructure and phase for the Si₃N₄ ceramics before and after heat-treatment, it was confirmed that oxidation did not occur at all or occurred only on the surface at a very insignificant level below 1,000 ℃. Based on this, it is concluded that the increase in the dielectric constant according to the temperature increase of Si₃N₄ ceramics is irrelevant to the oxidation behavior and is only due to the activation of charge polarization.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.18 no.4
• /
• pp.451-458
• /
• 2015

This paper handles self-collision avoidance for a rescue robot with redundant manipulators. In order to detect all available self-collisions in advance, minimum distances between arbitrary robot parts should be monitored in real-time. For the minimum distance estimation, we suggest a modified method from a previous skeleton algorithm which has less computation burden and realize collision avoidance based on a potential function using the proposed algorithm. The resultant command by collision avoidance should not disturb a given primary task, so null-space of joint solution from a CLIK is utilized for collision avoidance by a gradient projection method.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.115-122
• /
• 2024

Multi-object tracking (MOT) is a vital component in understanding the surrounding environments. Previous research has demonstrated that MOT can successfully detect and track surrounding objects. Nonetheless, inaccurate classification of the tracking objects remains a challenge that needs to be solved. When an object approaching from a distance is recognized, not only detection and tracking but also classification to determine the level of risk must be performed. However, considering the erroneous classification results obtained from the detection as the track class can lead to performance degradation problems. In this paper, we discuss the limitations of classification in tracking under the classification uncertainty of the detector. To address this problem, a class update module is proposed, which leverages the class uncertainty estimation of the detector to mitigate the classification error of the tracker. We evaluated our approach on the VisDrone-MOT2021 dataset,which includes multi-class and uncertain far-distance object tracking. We show that our method has low certainty at a distant object, and quickly classifies the class as the object approaches and the level of certainty increases.In this manner, our method outperforms previous approaches across different detectors. In particular, the You Only Look Once (YOLO)v8 detector shows a notable enhancement of 4.33 multi-object tracking accuracy (MOTA) in comparison to the previous state-of-the-art method. This intuitive insight improves MOT to track approaching objects from a distance and quickly classify them.