• 한국군사과학기술학회지
• /
• 제24권1호
• /
• pp.12-21
• /
• 2021

For successful automatic target recognition(ATR) with synthetic aperture radar(SAR) imagery, SAR target images of the database should have the identical or highly similar resolution with those collected from SAR sensors. However, it is time-consuming or infeasible to construct the multiple databases with different resolutions depending on the operating SAR system. In this paper, an approach for resolution conversion of SAR target images is proposed based on conditional generative adversarial network(cGAN). First, a number of pairs consisting of SAR target images with two different resolutions are obtained via SAR simulation and then used to train the cGAN model. Finally, the model generates the SAR target image whose resolution is converted from the original one. The similarity analysis is performed to validate reliability of the generated images. The cGAN model is further applied to measured MSTAR SAR target images in order to estimate its potential for real application.

• 정보보호학회논문지
• /
• 제30권5호
• /
• pp.871-879
• /
• 2020

Perceptual Ad-Blocking은 인공지능 기반의 광고 이미지 분류 모델을 이용하여 온라인 광고를 탐지하는 새로운 광고 차단 기법이다. 이러한 Perceptual Ad-Blocking은 최근 이미지 분류 모델이 이미지를 틀리게 분류하게 끔 이미지에 노이즈를 추가하는 적대적 예제(adversarial example)를 이용한 적대적 공격(adversarialbattack)에 취약하다는 연구 결과가 제시된 바 있다. 본 논문에서는 다양한 적대적 예제를 통해 기존 Perceptual Ad-Blocking 기법의 취약점을 증명하고, MNIST, CIFAR-10 등의 데이터 셋에서 성공적인 방어를 수행한 Defense-GAN과 MagNet이 광고 이미지에도 효과적으로 작용함을 보인다. 이를 통해 Defense-GAN과 MagNet 기법을 이용해 적대적 공격에 견고한 새로운 광고 이미지 분류 모델을 제시한다. 기존 다양한 적대적 공격 기법을 이용한 실험 결과에 따르면, 본 논문에서 제안하는 기법은 적대적 공격에 견고한 이미지 분류 기술을 통해 공격 이전의 이미지 분류 모델의 정확도와 성능을 확보할 수 있으며, 더 나아가 방어 기법의 세부사항을 아는 공격자의 화이트박스 공격(White-box attack)에도 일정 수준 방어가 가능함을 보였다.

• 국방과기술
• /
• 1호통권13호
• /
• pp.13-18
• /
• 1980

• 국방과기술
• /
• 8호통권20호
• /
• pp.6-13
• /
• 1980

• 국방과기술
• /
• 11호통권11호
• /
• pp.6-15
• /
• 1979

• 국방과기술
• /
• 12호통권12호
• /
• pp.7-19
• /
• 1979

• 정보보호학회논문지
• /
• 제33권3호
• /
• pp.449-458
• /
• 2023

인공지능은 빅데이터와 딥러닝 기술을 이용해 다양한 분야에서 삶의 편리함을 주고 있다. 하지만, 딥러닝 기술은 적대적 예제에 매우 취약하여 적대적 예제가 분류 모델의 오분류를 유도한다. 본 연구는 StarGAN을 활용해 다양한 적대적 공격을 탐지 및 정화하는 방법을 제안한다. 제안 방법은 Categorical Entropy loss를 추가한 StarGAN 모델에 다양한 공격 방법으로 생성된 적대적 예제를 학습시켜 판별자는 적대적 예제를 탐지하고, 생성자는 적대적 예제를 정화한다. CIFAR-10 데이터셋을 통해 실험한 결과 평균 탐지 성능은 약 68.77%, 평균정화성능은 약 72.20%를 보였으며 정화 및 탐지 성능으로 도출되는 평균 방어 성능은 약 93.11%를 보였다.

• International journal of advanced smart convergence
• /
• 제8권1호
• /
• pp.141-146
• /
• 2019

These days, there are many applications using neural networks as parts of their system. On the other hand, adversarial examples have become an important issue concerining the security of neural networks. A classifier in neural networks can be fooled and make it miss-classified by adversarial examples. There are many research to encounter adversarial examples by using denoising methods. Some of them using GAN (Generative Adversarial Network) in order to remove adversarial noise from input images. By producing an image from generator network that is close enough to the original clean image, the adversarial examples effects can be reduced. However, there is a chance when adversarial noise can survive the approximation process because it is not like a normal noise. In this chance, we propose a research that utilizes high-level representation in the classifier by combining GAN network with a trained U-Net network. This approach focuses on minimizing the loss function on high representation terms, in order to minimize the difference between the high representation level of the clean data and the approximated output of the noisy data in the training dataset. Furthermore, the generated output is checked whether it shows minimum error compared to true label or not. U-Net network is trained with true label to make sure the generated output gives minimum error in the end. At last, the remaining adversarial noise that still exist after low-level approximation can be removed with the U-Net, because of the minimization on high representation terms.

• Current Optics and Photonics
• /
• 제5권4호
• /
• pp.391-401
• /
• 2021

In the present study, a hyperelastic constitutive model is built by complying with a simplified hyperelastic strain energy function, which yields the numerical solution for a deformed polydimethylsiloxane (PDMS) membrane in the case of axisymmetric hydraulic pressure. Moreover, a nonlinear equilibrium model is deduced to accurately express the deformation of the membrane, laying a basis for precise analysis of the optical transfer function. Comparison to experimental and simulated data suggests that the model is capable of accurately characterizing the deformation behavior of the membrane. Furthermore, the stretch ratio derived from the model applies to the geometrical optimization of the deformed membrane.

• Current Optics and Photonics
• /
• 제4권4호
• /
• pp.277-285
• /
• 2020

Computer-generated holograms (CGH) are the core devices to solve the problem of freeform surface measurement. In view of the overlay error introduced in the manufacturing process of CGH, this paper proposes an evaluation model for analyzing the overlay error of CGH. The detection method of extracting CGH profile information by an ultra-depth of field micro-measurement system is presented. Furthermore, based on the detection method and technical scheme, the effect of overlay error on the wavefront accuracy of CGH can be evaluated.