• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.997-1008
• /
• 2022

Today, AI(Artificial Intelligence) technology is being extensively researched in various fields, including the field of malware detection. To introduce AI systems into roles that protect important decisions and resources, it must be a reliable AI model. AI model that dependent on training dataset should be verified to be robust against new attacks. Rather than generating new malware detection, attackers find malware detection that succeed in attacking by mass-producing strains of previously detected malware detection. Most of the attacks, such as adversarial attacks, that lead to misclassification of AI models, are made by slightly modifying past attacks. Robust models that can be defended against these variants is needed, and the Robustness level of the model cannot be evaluated with accuracy and recall, which are widely used as AI evaluation indicators. In this paper, we experiment a framework to evaluate robustness level by generating an adversarial sample based on one of the adversarial attacks, C&W attack, and to improve robustness level through adversarial training. Through experiments based on malware dataset in this study, the limitations and possibilities of the proposed method in the field of malware detection were confirmed.

• Nuclear Engineering and Technology
• /
• v.56 no.6
• /
• pp.1989-2001
• /
• 2024

Artificial intelligence (AI) techniques are now being considered in the nuclear field, but application faces with the lack of actual plant data. For this reason, most previous studies on AI applications in nuclear power plants (NPPs) have relied on simulators or thermal-hydraulic codes to mimic the plants. However, it remains uncertain whether an AI model trained using a simulator can properly work in an actual NPP. To address this issue, this study suggests the use of metadata, which can give information about parameter trends. Referred to here as robust AI, this concept started with the idea that although the absolute value of a plant parameter differs between a simulator and actual NPP, the parameter trend is identical under the same scenario. Based on the proposed robust AI, this study designs an event diagnosis algorithm to classify abnormal and emergency scenarios in NPPs using prototypical learning. The algorithm was trained using a simulator referencing a Westinghouse 990 MWe reactor and then tested in different environments in Advanced Power Reactor 1400 MWe simulators. The algorithm demonstrated robustness with 100 % diagnostic accuracy (117 out of 117 scenarios). This indicates the potential of the robust AI-based algorithm to be used in actual plants.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.4
• /
• pp.474-484
• /
• 2024

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.136-138
• /
• 2022

스포츠 방송/미디어 데이터에서 특정 이벤트 시점을 효율적으로 검출하는 방법은 정보 검색이나 하이라이트, 요약 등을 위해 중요한 기술이다. 이 논문에서는, 야구 중계 방송 데이터에서 투구에 대한 타격 및 포구 이벤트 시점을 강인하게 검출하는 방법으로, 음향 및 영상 정보를 융합하는 방법에 대해 제안한다. 음향 정보에 기반한 이벤트 검출 방법은 계산이 용이하고 정확도가 높은 반면, 영상 정보의 도움 없이는 모호성을 해결하기 힘든 경우가 많이 발생한다. 특히 야구 중계 데이터의 경우, 투수의 투구 시점에 대한 영상 정보를 활용하여 타격 및 포구 이벤트 검출의 정확도를 보다 향상시킬 수 있다. 이 논문에서는 음향 기반의 딥러닝 이벤트 시점 검출 모델과 영상 기반의 보정 방법을 제안하고, 실제 KBO 야구 중계 방송 데이터에 적용한 사례와 실험 결과에 대해 기술한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.337-340
• /
• 2024

Pretrained language models (PLMs) are extensively utilized to enhance the performance of log anomaly detection systems. Their effectiveness lies in their capacity to extract valuable semantic information from logs, thereby strengthening the detection performance. Nonetheless, challenges arise due to discrepancies in the distribution of log messages, hindering the development of robust and generalizable detection systems. This study investigates the structural and distributional variation across various log message datasets, underscoring the crucial role of domain-specific PLMs in overcoming the said challenge and devising robust and generalizable solutions.

• Electronics and Telecommunications Trends
• /
• v.39 no.4
• /
• pp.21-31
• /
• 2024

Major global powers are investing heavily in artificial intelligence (AI) and hyper-connected networks, demonstrating their crucial role in future warfare. To advance and utilize AI in national defense, it is essential to have policy support at the governmental or national level. This includes establishing a research and development infrastructure, creating a common development environment, and fostering AI expertise through education and training programs. To achieve advancements in hyper-connected networks, it is essential to establish a foundation for a robust and resilient infrastructure by comprehensively building integrated satellite, aerial, and ground networks, along with developing 5G & edge computing and low-orbit satellite communication technologies. This multi-faceted approach will ensure the successful integration of AI and hyper-connected networks, strengthening national defense and positioning nations at the forefront of technological advancements in warfare.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.41-46
• /
• 2021

기계 독해는 문단과 질문이 주어질 때에 정답을 맞추는 자연어처리의 연구분야다. 최근 기계 독해 모델이 사람보다 높은 성능을 보여주고 있지만, 문단과 질의가 크게 변하지 않더라도 예상과 다른 결과를 만들어 성능에 영향을 주기도 한다. 본 논문에서는 문단과 질문 두 가지 관점에서 적대적 예시 데이터를 사용하여 보다 강건한 질의응답 모델을 훈련하는 방식을 제안한다. 트랜스포머 인코더 모델을 활용하였으며, 데이터를 생성하기 위해서 KorQuAD 1.0 데이터셋에 적대적 예시를 추가하여 실험을 진행하였다. 적대적 예시를 이용한 데이터로 실험한 결과, 기존 모델보다 1% 가량 높은 성능을 보였다. 또한 질의의 적대적 예시 데이터를 활용하였을 때, 기존 KorQuAD 1.0 데이터에 대한 성능 향상을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.557-560
• /
• 2023

In this paper, we introduce a pre-training method leveraging the capabilities of the Vision Transformer (ViT) for disease diagnosis in conventional Fundus images. Recognizing the need for effective representation learning in medical images, our method combines the Vision Transformer with a Masked Autoencoder to generate meaningful and pertinent image augmentations. During pre-training, the Masked Autoencoder produces an altered version of the original image, which serves as a positive pair. The Vision Transformer then employs contrastive learning techniques with this image pair to refine its weight parameters. Our experiments demonstrate that this dual-model approach harnesses the strengths of both the ViT and the Masked Autoencoder, resulting in robust and clinically relevant feature embeddings. Preliminary results suggest significant improvements in diagnostic accuracy, underscoring the potential of our methodology in enhancing automated disease diagnosis in fundus imaging.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.25-36
• /
• 2023

Today, as AI (Artificial Intelligence) technology is introduced in various fields, including security, the development of technology is accelerating. However, with the development of AI technology, attack techniques that cleverly bypass malicious behavior detection are also developing. In the classification process of AI models, an Adversarial attack has emerged that induces misclassification and a decrease in reliability through fine adjustment of input values. The attacks that will appear in the future are not new attacks created by an attacker but rather a method of avoiding the detection system by slightly modifying existing attacks, such as Adversarial attacks. Developing a robust model that can respond to these malware variants is necessary. In this paper, we propose two methods of generating Adversarial attacks as efficient Adversarial attack generation techniques for improving Robustness in AI models. The proposed technique is the XAI-based attack technique using the XAI technique and the Reference based attack through the model's decision boundary search. After that, a classification model was constructed through a malicious code dataset to compare performance with the PGD attack, one of the existing Adversarial attacks. In terms of generation speed, XAI-based attack, and reference-based attack take 0.35 seconds and 0.47 seconds, respectively, compared to the existing PGD attack, which takes 20 minutes, showing a very high speed, especially in the case of reference-based attack, 97.7%, which is higher than the existing PGD attack's generation rate of 75.5%. Therefore, the proposed technique enables more efficient Adversarial attacks and is expected to contribute to research to build a robust AI model in the future.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.229-237
• /
• 2023

In this research, a new Test and Evaluation (T&E) procedure for defense AI systems is proposed to fill the existing gap in established methodologies. This proposed concept incorporates a data-based performance evaluation, allowing for independent assessment of AI model efficacy. It then follows with an on-site T&E using the actual AI system. The performance evaluation approach adopts the project promotion framework from the defense acquisition system, outlining 10 steps for R&D projects and 9 steps for procurement projects. This procedure was crafted after examining AI system testing standards and guidelines from both domestic and international civilian sectors. The validity of each step in the procedure was confirmed using real-world data. This study's findings aim to offer insightful guidance in defense T&E, particularly in developing robust T&E procedures for defense AI systems.