• Smart Media Journal
• /
• v.7 no.4
• /
• pp.61-69
• /
• 2018

Multi-tracking of general objects and specific faces is an important topic in the field of computer vision applicable to many branches of industry such as biometrics, security, etc. The rapid development of deep neural networks has resulted in a dramatic improvement in face recognition and object detection problems, which helps improve the multiple-face tracking techniques exploiting the tracking-by-detection method. Our proposed method uses face detection trained with a head dataset to resolve the face deformation problem in the tracking process. Further, we use robust face features extracted from the deep face recognition network to match the tracklets with tracking faces using Hungarian matching method. We achieved promising results regarding the usage of deep face features and head detection in a face tracking benchmark.

• Journal of Internet Computing and Services
• /
• v.20 no.3
• /
• pp.25-31
• /
• 2019

Along with the recent advances in quantum computers, it is anticipated that cryptographic attacks using them will make it insecure to use existing public key algorithms such as RSA and ECC. Currently, a lot of researches are underway to replace them by devising PQC (Post Quantum Cryptography) schemes. In this paper, we propose a performance enhancement method for Lizard implementation which is one of NIST PQC standardization submission. The proposed method is able to improve the performance by 7 ~ 25% for its algorithms compared to the implementation in the submission through the techniques of various implementation aspects. This study hopes that Lizard will become more competitive as a candidate for PQC standardization.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.345-354
• /
• 2021

Recently, deep learning-based image recognition systems have been adopted to various surveillance environments, but most of them are still picture-type object recognition methods, which are insufficient for the long term temporal analysis and high-dimensional situation management. Therefore, we propose a method recognizing the specific dangerous situation generated by human in real-time, and utilizing deep learning-based object analysis techniques. The proposed method uses deep learning-based object detection and tracking algorithms in order to recognize the situations such as 'trespassing', 'loitering', and so on. In addition, human's joint pose data are extracted and analyzed for the emergent awareness function such as 'falling down' to notify not only in the security but also in the emergency environmental utilizations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.986-1005
• /
• 2022

Text steganography is one of the most imminent and promising research interests in the information security field. With the unprecedented success of the neural network and natural language processing (NLP), the last years have seen a surge of research on generative linguistic steganography (GLS). This paper provides a thorough and comprehensive review to summarize the existing key contributions, and creates a novel taxonomy for GLS according to NLP techniques and steganographic encoding algorithm, then summarizes the characteristics of generative linguistic steganographic methods properly to analyze the relationship and difference between each type of them. Meanwhile, this paper also comprehensively introduces and analyzes several evaluation metrics to evaluate the performance of GLS from diverse perspective. Finally, this paper concludes the future research work, which is more conducive to the follow-up research and innovation of researchers.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.479-482
• /
• 2022

Recently, various artificial intelligence technologies are being applied to smart factory, finance, healthcare, and so on. When handling data requiring protection of privacy, distributed learning techniques are used. For distribution of information with privacy protection, encoding private information is required. Minimal codes has been used in such a secret-sharing scheme. In this paper, we explain the relationship between the characteristics of the minimal codes for application in distributed systems. We briefly deals with previously known construction methods, and presents extension methods for minimal codes. The new codes provide flexibility in distribution of private information. Furthermore, we discuss application scenarios for the extended codes.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.365-366
• /
• 2022

The distributed code is a type of linear codes that can be used for coding and federated learning for privacy. In the distributed code, privacy or confidential information is not dependent to each other because the information of each code is not included with other codes. In this paper, we examine the properties of these distributed codes and present techniques for synthesizing new sets of distributed codes from previously known distributed codes. In addition, we propose several scenarios in which combined codes can be used.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.1022-1024
• /
• 2022

최근 인공지능 기술이 급격하게 발전하고 빠르게 보급되면서, 머신러닝 시스템을 대상으로 한 다양한 공격들이 등장하기 시작하였다. 인공지능은 많은 강점이 있지만 인위적인 조작에 취약할 수 있기 때문에, 그만큼 이전에는 존재하지 않았던 새로운 위험을 내포하고 있다고 볼 수 있다. 본 논문에서는 데이터 유형 별 적대적 공격 샘플을 직접 제작하고 이에 대한 효과적인 방어법을 구현하였다. 영상 및 텍스트 데이터를 기반으로 한 적대적 샘플공격을 방어하기 위해 적대적 훈련기법을 적용하였고, 그 결과 공격에 대한 면역능력이 형성된 것을 확인하였다.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.29-32
• /
• 2023

양자 컴퓨터의 연산 성능이 알려지면서 기존 암호 시스템이 붕괴될 것이라 예상한다. 앞선 많은 연구들은 공격 대상 암호에 대해 양자회로로 구현하고 공격에 필요한 양자자원을 추정하였지만 암호를 공격하기 위해서는 대규모 양자컴퓨터의 동작을 요구한다. 뿐만 아니라 내결함성 양자 컴퓨터에서 유효한 결과를 얻기 위해서는 오류 정정이 필수적이며 오류 정정에도 양자 자원을 소비하며 결과적으로 더 큰 규모의 양자컴퓨터가 필요하고 크기가 커질수록 오류가 증가한다. 이러한 내결함성 대규모 양자회로에서 T 게이트를 구현하는 것이 다른 게이트를 구현하는 것 보다 어렵고 T-depth가 회로의 실행시간에 큰 영향을 미친다. 본 논문에서는 T-depth 최적화 도구 및 T-depth 감소 기법을 적용한 방식을 조사하였다.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.16-24
• /
• 2024

With an increase in the relevance of next-generation integrated networking environments, the need to effectively utilize advanced networking techniques also increases. Specifically, integrating Software-Defined Networking (SDN) with Multi-access Edge Computing (MEC) is critical for enhancing network flexibility and addressing challenges such as security vulnerabilities and complex network management. SDN enhances operational flexibility by separating the control and data planes, introducing management complexities. This paper proposes a reinforcement learning-based network path optimization strategy within SDN environments to maximize performance, minimize latency, and optimize resource usage in MEC settings. The proposed Enhanced Proximal Policy Optimization (PPO)-based scheme effectively selects optimal routing paths in dynamic conditions, reducing average delay times to about 60 ms and lowering energy consumption. As the proposed method outperforms conventional schemes, it poses significant practical applications.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.1
• /
• pp.110-116
• /
• 2024

Despite the continuous advancement of science and technology, fire accidents continue to occur without decreasing over time, so there is a constant need for a system that can accurately detect fires at an early stage. However, because most existing fire detection systems detect fire in the early stage of combustion when smoke is generated, rapid fire prevention actions may be delayed. Therefore we propose an early fire detection system that can perform early fire detection at a reasonable cost using LSTM, a deep learning model based on multi-gas sensors with high selectivity in the early stage of decomposition rather than the smoke generation stage. This system combines multiple gas sensors to achieve faster detection speeds than traditional sensors. In addition, through window sliding techniques and model light-weighting, the false alarm rate is low while maintaining the same high accuracy as existing deep learning. This shows that the proposed fire early detection system is a meaningful research in the disaster and engineering fields.