오늘날 기업 및 산업 분야에서 클라우드 컴퓨팅 기술의 활용이 증가함에 따라 클라우드 컴퓨팅 기술의 취약점을 활용한 보안 위협 문제가 대두되고 있다. 이에 대응하기 위해, 클라우드 이...

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
https://www.riss.kr/link?id=A109207618
2024
Korean
클라우드 시스템 보안 ; 이상 탐지 ; 딥러닝 ; 적대적 공격 ; NSL-MHA ; Cloud System Security ; Anomaly Detection ; Deep Learning ; Adversarial Attack ; NSL-MHA
KCI등재
학술저널
347-355(9쪽)
0
상세조회0
다운로드오늘날 기업 및 산업 분야에서 클라우드 컴퓨팅 기술의 활용이 증가함에 따라 클라우드 컴퓨팅 기술의 취약점을 활용한 보안 위협 문제가 대두되고 있다. 이에 대응하기 위해, 클라우드 이...
오늘날 기업 및 산업 분야에서 클라우드 컴퓨팅 기술의 활용이 증가함에 따라 클라우드 컴퓨팅 기술의 취약점을 활용한 보안 위협 문제가 대두되고 있다. 이에 대응하기 위해, 클라우드 이상 행위 탐지 기술의 중요성이 강조되고 있다. 최근 연구에 따르면, CNN 모델 기반 이상 행위 탐지 기술은 우수한 탐지 성능을 보이는 것을 입증하였다. 그러나, CNN 모델 기반이상 행위 탐지 기술은 적대적 공격에 취약하다는 단점이 존재한다. 따라서, 본 논문에서는NSL-MHA 적대적 훈련 기법을 제안하여 CNN 모델 기반 이상 행위 탐지 기술의 적대적공격 취약점을 극복하고자 한다. 실험을 통해 NSL-MHA 적대적 훈련 기법이 CNN 모델 기반 이상 행위 탐지 기술의 적대적 공격 취약성을 극복함을 검증하였다.
다국어 초록 (Multilingual Abstract)
"As the utilization of cloud computing techniques increases in today’s enterprises and industries, security threats exploiting the vulnerabilities of cloud computing techniques have become a significant concern. In response, the importance of anomal...
"As the utilization of cloud computing techniques increases in today’s enterprises and industries, security threats exploiting the vulnerabilities of cloud computing techniques have become a significant concern. In response, the importance of anomaly detection techniques in cloud computing is being emphasized. Recent research has demonstrated that CNN model-based anomaly detection techniques achieve excellent detection performance. However, a drawback of these techniques is their vulnerability to adversarial attacks. Therefore, this paper proposes the NSL-MHA adversarial training method to overcome the vulnerabilities of CNN-based anomaly detection techniques against adversarial attacks. From the experimental results, it was verified that the NSL-MHA adversarial training method overcomes the drawbacks of CNN model-based anomaly detection techniques."
참고문헌 (Reference)
1 Andriushchenko, Maksym, "Understanding and improving fast adversarial training" 33 : 16048-16059, 2020
2 Shaham, Uri, "Understanding adversarial training : Increasing local stability of neural nets through robust optimization"
3 Xu, Weilin, "Feature squeezing : Detecting adversarial examples in deep neural networks"
4 Goodfellow, "Explaining and harnessing adversarial examples"
5 Abou Khamis, Rana, "Evaluation of adversarial training on different types of neural networks in deep learning-based idss" 1-6, 2020
6 Tramèr, Florian, "Ensemble adversarial training : Attacks and defenses"
7 Ferrag, Mohamed Amine, "Edge-IIoTset : A new comprehensive realistic cyber security dataset of IoT and IIoT applications for centralized and federated learning" 10 : 40281-40306, 2022
8 Papernot, Nicolas, "Distillation as a defense to adversarial perturbations against deep neural networks" 582-597, 2016
9 Albattah, Albatul, "Detection of Adversarial Attacks against the Hybrid Convolutional Long Short-Term Memory Deep Learning Technique for Healthcare Monitoring Applications" 13 (13): 2023
10 Zhang, Xianchao, "Deep anomaly detection with self-supervised learning and adversarial training" 121 : 108234-, 2022
1 Andriushchenko, Maksym, "Understanding and improving fast adversarial training" 33 : 16048-16059, 2020
2 Shaham, Uri, "Understanding adversarial training : Increasing local stability of neural nets through robust optimization"
3 Xu, Weilin, "Feature squeezing : Detecting adversarial examples in deep neural networks"
4 Goodfellow, "Explaining and harnessing adversarial examples"
5 Abou Khamis, Rana, "Evaluation of adversarial training on different types of neural networks in deep learning-based idss" 1-6, 2020
6 Tramèr, Florian, "Ensemble adversarial training : Attacks and defenses"
7 Ferrag, Mohamed Amine, "Edge-IIoTset : A new comprehensive realistic cyber security dataset of IoT and IIoT applications for centralized and federated learning" 10 : 40281-40306, 2022
8 Papernot, Nicolas, "Distillation as a defense to adversarial perturbations against deep neural networks" 582-597, 2016
9 Albattah, Albatul, "Detection of Adversarial Attacks against the Hybrid Convolutional Long Short-Term Memory Deep Learning Technique for Healthcare Monitoring Applications" 13 (13): 2023
10 Zhang, Xianchao, "Deep anomaly detection with self-supervised learning and adversarial training" 121 : 108234-, 2022
11 Jonghyun Lee, "CrowdStrike, 2023 Threat Hunting Report"
12 정현진 ; 홍석원 ; 김진성 ; 최석환, "Cloud Anomaly Detection Method Using 1-D STM Block-based Stacking CNN Model" 34 (34): 43-50, 2024
13 Alatwi, Huda Ali, "Adversarial machine learning in network intrusion detection domain : A systematic review"
14 Chakraborty, Anirban, "Adversarial attacks and defences : A survey"
15 Yin, Zhizhou, "Adversarial attack, defense, and applications with deep learning frameworks" 1-25, 2019
16 Sah, Ramesh Kumar, "Adar : Adversarial activity recognition in wearables" 1-8, 2019
17 Lyu, Chunchuan, "A unified gradient regularization family for adversarial examples" 301-309, 2015
Sharpness-Aware Minimization을 적용한 Separable Vision Transformer 기반 악성코드 유형 분류 기법
로그인하고 관련된 다양한 학술자료를 확인해 보세요.
로그인