Digital Library
Search: "[ keyword: Deep Learning ]" (46)
CNN을 이용한 소비 전력 파형 기반 명령어 수준 역어셈블러 구현
배대현,
하재철,
Vol. 30, No. 4, pp. 527-536,
8월.
2020
10.13089/JKIISC.2020.30.4.527
주제어: Side-Channel Attack, power analysis, Deep Learning, Convolutional Neural Network(CNN), Disassembl, Side-Channel Attack, power analysis, Deep Learning, Convolutional Neural Network(CNN), Disassembl
10.13089/JKIISC.2020.30.4.527
주제어: Side-Channel Attack, power analysis, Deep Learning, Convolutional Neural Network(CNN), Disassembl, Side-Channel Attack, power analysis, Deep Learning, Convolutional Neural Network(CNN), Disassembl
STFT와 RNN을 활용한 화자 인증 모델
김민서,
문종섭,
Vol. 29, No. 6, pp. 1393-1401,
12월.
2019
10.13089/JKIISC.2019.29.6.1393
주제어: Speaker verification, STFT, Deep Learning, Recurrent Neural Network(RNN), Speaker verification, STFT, Deep Learning, Recurrent Neural Network(RNN)
10.13089/JKIISC.2019.29.6.1393
주제어: Speaker verification, STFT, Deep Learning, Recurrent Neural Network(RNN), Speaker verification, STFT, Deep Learning, Recurrent Neural Network(RNN)
감쇠 요소가 적용된 데이터 어그멘테이션을 이용한 대체 모델 학습과 적대적 데이터 생성 방법
민정기,
문종섭,
Vol. 29, No. 6, pp. 1383-1392,
12월.
2019
10.13089/JKIISC.2019.29.6.1383
주제어: Deep Learning, Adversarial Data Generation, data augmentation, Deep Learning, Adversarial Data Generation, data augmentation
10.13089/JKIISC.2019.29.6.1383
주제어: Deep Learning, Adversarial Data Generation, data augmentation, Deep Learning, Adversarial Data Generation, data augmentation
Multi-Layer Perceptron 기법을 이용한 전력 분석 공격 구현 및 분석
권홍필,
배대현,
하재철,
Vol. 29, No. 5, pp. 997-1006,
10월.
2019
10.13089/JKIISC.2019.29.5.997
주제어: Side-Channel Analysis, Power Analysis Attack, Deep Learning MLP, Machine Learning SVM, Side-Channel Analysis, Power Analysis Attack, Deep Learning MLP, Machine Learning SVM
10.13089/JKIISC.2019.29.5.997
주제어: Side-Channel Analysis, Power Analysis Attack, Deep Learning MLP, Machine Learning SVM, Side-Channel Analysis, Power Analysis Attack, Deep Learning MLP, Machine Learning SVM
네트워크 데이터 정형화 기법을 통한 데이터 특성 기반 기계학습 모델 성능평가
이우호,
노봉남,
정기문,
Vol. 29, No. 4, pp. 785-794,
8월.
2019
10.13089/JKIISC.2019.29.4.785
주제어: IDS, Deep Learning, Data normalize
10.13089/JKIISC.2019.29.4.785
주제어: IDS, Deep Learning, Data normalize
비프로파일링 기반 전력 분석의 성능 향상을 위한 오토인코더 기반 잡음 제거 기술
권동근,
진성현,
김희석,
홍석희,
Vol. 29, No. 3, pp. 491-501,
5월.
2019
10.13089/JKIISC.2019.29.3.491
주제어: Side-Channel Analysis, Non-Profiled Attack, Deep Learning, Auto-Encoder, Preprocessing, Side-Channel Analysis, Non-Profiled Attack, Deep Learning, Auto-Encoder, Preprocessing
10.13089/JKIISC.2019.29.3.491
주제어: Side-Channel Analysis, Non-Profiled Attack, Deep Learning, Auto-Encoder, Preprocessing, Side-Channel Analysis, Non-Profiled Attack, Deep Learning, Auto-Encoder, Preprocessing
공개 딥러닝 라이브러리에 대한 보안 취약성 검증
정재한,
손태식,
Vol. 29, No. 1, pp. 117-125,
1월.
2019
10.13089/JKIISC.2019.29.1.117
주제어: Adversarial attack, MNIST, Deep Learning, Security, Autoencoder, Convolution Neural Network, Adversarial attack, MNIST, Deep Learning, Security, Autoencoder, Convolution Neural Network
10.13089/JKIISC.2019.29.1.117
주제어: Adversarial attack, MNIST, Deep Learning, Security, Autoencoder, Convolution Neural Network, Adversarial attack, MNIST, Deep Learning, Security, Autoencoder, Convolution Neural Network
Variational Autoencoder를 활용한 필드 기반 그레이 박스 퍼징 방법
이수림,
문종섭,
Vol. 28, No. 6, pp. 1463-1474,
11월.
2018
10.13089/JKIISC.2018.28.6.1463
주제어: Software Testing, Fuzzing, Vulnerability, Deep Learning, VAE(Variational Autoencoder), Software Testing, Fuzzing, Vulnerability, Deep Learning, VAE(Variational Autoencoder)
10.13089/JKIISC.2018.28.6.1463
주제어: Software Testing, Fuzzing, Vulnerability, Deep Learning, VAE(Variational Autoencoder), Software Testing, Fuzzing, Vulnerability, Deep Learning, VAE(Variational Autoencoder)
