• 한국정보통신학회논문지
• /
• 제25권9호
• /
• pp.1271-1274
• /
• 2021

RF fingerprinting based on deep learning (DL) has gained interests as a means to improve the security of near field communication (NFC) by allowing identification of NFC tags based on unique physical characteristics. To achieve high accuracy in the identification of NFC tags, it is crucial to utilize a large number of training data, however it is hard to collect such dataset in practice. In this study, we have provided new methodology to generate RF waveform from NFC tags, i.e., data augmentation, based on a conditional generative adversarial network (CGAN). By using the RF waveform of NFC tags which is collected from the testbed with software defined radio (SDR), we have confirmed that the realistic RF waveform can be generated through our proposed scheme.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4326-4344
• /
• 2021

The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.

• 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.

• 한국컴퓨터정보학회논문지
• /
• 제29권3호
• /
• pp.11-20
• /
• 2024

AI(Artificial Intelligence)의 다양한 모델 중 생성 모델, 특히 GAN(Generative Adversarial Network)은 이미지 처리, 밀도 추정, 스타일 전이 등 다양한 응용 분야에서 성공을 거두었다. 이러한 GAN은 CGAN(Conditional GAN), CycleGAN, BigGAN 등의 방식으로 확장 및 개선되었지만 재난 시뮬레이션, 의료 분야, 도시 계획 등 특정 분야에서는 데이터 부족과 불안정한 학습에 의한 이미지 왜곡 문제로 실제 시스템 적용에 문제가 되고 있다. 본 논문에서는 클래스 항목을 판별하는 ACGAN(Auxiliary Classifier GAN) 구조를 기반으로 기존 PGGAN(Progressive Growing of GAN)의 점진적 학습 방식을 활용한 새로운 점진적 단계의 학습 방법론 PST(Progressive Step Training)를 제안한다. PST 모델은 기존 방법 대비 70.82% 빠른 안정화, 51.3% 낮은 표준 편차, 후반 고해상도의 안정적 손실값 수렴 그리고 94.6% 빠른 손실 감소를 달성한다.

• 대한원격탐사학회지
• /
• 제38권1호
• /
• pp.33-43
• /
• 2022

This study presents a method to restore an optical satellite image with distortion and occlusion due to fog, haze, and clouds to one that minimizes degradation factors by referring to the same type of peripheral image. Specifically, the time and cost of re-photographing were reduced by partially occluding a region. To maintain the original image's pixel value as much as possible and to maintain restored and unrestored area continuity, a simulation restoration technique modified with the Cycle Generative Adversarial Network (CycleGAN) method was developed. The accuracy of the simulated image was analyzed by comparing CycleGAN and histogram matching, as well as the pixel value distribution, with the original image. The results show that for Site 1 (out of three sites), the root mean square error and R² of CycleGAN were 169.36 and 0.9917, respectively, showing lower errors than those for histogram matching (170.43 and 0.9896, respectively). Further, comparison of the mean and standard deviation values of images simulated by CycleGAN and histogram matching with the ground truth pixel values confirmed the CycleGAN methodology as being closer to the ground truth value. Even for the histogram distribution of the simulated images, CycleGAN was closer to the ground truth than histogram matching.

• 한국전자통신학회논문지
• /
• 제17권2호
• /
• pp.291-298
• /
• 2022

생성적 적대 신경망(Generative Adversarial Networks, GAN)은 내부의 두 신경망(생성망, 판별망)이 상호 경쟁하면서 학습하는 네트워크이다. 생성자는 현실과 가까운 이미지를 만들고, 구분자는 생성자의 이미지를 더 잘 감별하도록 프로그래밍 되어있다. 이 기술은 전체 이미지 X를 다른 이미지 Y로 생성, 변환 및 복원하기 위해 다양하게 활용되고 있다. 본 논문에서는 원본 이미지에서 부분 이미지만 추출한 후, 이를 자연스럽게 다른 객체로 위변조할 수 있는 방법에 관해 기술한다. 먼저 원본 이미지에서 부분 이미지만 추출한 후, 기존에 학습시켜놓은 DCGAN 모델을 통해 새로운 이미지를 생성하고, 이를 전체적 스타일 전이(overall style transfer) 기술을 사용하여 원본 이미지의 질감과 크기에 어울리도록 리스타일링(re-styling) 한 후, 원본 이미지에 자연스럽게 결합하는 과정을 거친다. 본 연구를 통해 원본 이미지의 특정 부분에 사용자가 원하는 객체 이미지를 자연스럽게 추가/변형할 수 있음으로써 가짜 이미지 생성의 또 다른 활용 분야로 사용될 수 있을 것이다.

• 방송공학회논문지
• /
• 제23권4호
• /
• pp.503-510
• /
• 2018

손상된 영상의 복원은 디지털 영상 처리기술이 등장하기 이전부터 시도되었던 근원적 문제이다. 컴퓨터의 연산 능력과 다양한 기술의 발전에 따라 손상된 영상을 복원하는 다양한 연구가 소개되었으나 그 결과는 사람에 의한 수동적 결과물과 비교하여 낮은 복원 결과를 보여 왔다. 최근 심층 신경망 (DNN, Deep Neural Network)의 발전으로 이미지 복원에 이를 적용한 다양한 연구가 소개 되고 있지만, 광범위한 영역이 손상된 경우 근접한 화소를 활용하는 방법으로 해결이 어렵다. 이와 같은 경우는 주변의 영상의 문맥적 정보를 통해 손상된 영역을 추론을 통한 복원이 필요하다. 본 논문에서는 심층 신경망 기술 중 하나인 적대적 생성신경망(GAN, Generative Adversarial Network)을 이용한 이미지 복원 네트워크를 제안한다. 제안하는 시스템은 이미지 생성 네트워크, 생성 결과 판별 네트워크로 구성 된다. 본 논문에서는 제안하는 방안을 통해 다양한 종류의 이미지를 복원함에 있어서 훼손된 영역의 추론을 통하여 자연스러운 영상 복원뿐 아니라 원본 영상의 질감까지 복원이 가능함을 실험을 통해 확인 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.456-477
• /
• 2024

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.37-42
• /
• 2019

In this paper, we explore the details of three classic data augmentation methods and two generative model based oversampling methods. The three classic data augmentation methods are random sampling (RANDOM), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN). The two generative model based oversampling methods are Conditional Generative Adversarial Network (CGAN) and Wasserstein Generative Adversarial Network (WGAN). In imbalanced data, the whole instances are divided into majority class and minority class, where majority class occupies most of the instances in the training set and minority class only includes a few instances. Generative models have their own advantages when they are used to generate more plausible samples referring to the distribution of the minority class. We also adopt CGAN to compare the data augmentation performance with other methods. The experimental results show that WGAN-based oversampling technique is more stable than other approaches (RANDOM, SMOTE, ADASYN and CGAN) even with the very limited training datasets. However, when the imbalanced ratio is too small, generative model based approaches cannot achieve satisfying performance than the conventional data augmentation techniques. These results suggest us one of future research directions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4105-4121
• /
• 2021

Recently, malware classification based on Deep Neural Networks (DNN) has gained significant attention due to the rise in popularity of artificial intelligence (AI). DNN-based malware classifiers are a novel solution to combat never-before-seen malware families because this approach is able to classify malwares based on structural characteristics rather than requiring particular signatures like traditional malware classifiers. However, these DNN-based classifiers have been found to lack robustness against malwares that are carefully crafted to evade detection. These specially crafted pieces of malware are referred to as adversarial examples. We consider a clever adversary who has a thorough knowledge of DNN-based malware classifiers and will exploit it to generate a crafty malware to fool DNN-based classifiers. In this paper, we propose a DNN-based malware classifier that becomes resilient to these kinds of attacks by exploiting Generative Adversarial Network (GAN) based data augmentation. The experimental results show that the proposed scheme classifies malware, including AEs, with a false positive rate (FPR) of 3.0% and a balanced accuracy of 70.16%. These are respective 26.1% and 18.5% enhancements when compared to a traditional DNN-based classifier that does not exploit GAN.