• 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.31-36
• /
• 2019

Unsupervised neural networks have not caught enough attention until Generative Adversarial Network (GAN) was proposed. By using both the generator and discriminator networks, GAN can extract the main characteristic of the original dataset and produce new data with similarlatent statistics. However, researchers understand fully that training GAN is not easy because of its unstable condition. The discriminator usually performs too good when helping the generator to learn statistics of the training datasets. Thus, the generated data is not compelling. Various research have focused on how to improve the stability and classification accuracy of GAN. However, few studies delve into how to improve the training efficiency and to save training time. In this paper, we propose a novel optimizer, named FAST-ADAM, which integrates the Lookahead to ADAM optimizer to train the generator of a semi-supervised generative adversarial network (SSGAN). We experiment to assess the feasibility and performance of our optimizer using Canadian Institute For Advanced Research - 10 (CIFAR-10) benchmark dataset. From the experiment results, we show that FAST-ADAM can help the generator to reach convergence faster than the original ADAM while maintaining comparable training accuracy results.

• 국제초고층학회논문집
• /
• 제12권3호
• /
• pp.203-208
• /
• 2023

The implementation of artificial intelligence (AI) design for tall building structures is an essential solution for addressing critical challenges in the current structural design industry. Generative AI technology is a crucial technical aid because it can acquire knowledge of design principles from multiple sources, such as architectural and structural design data, empirical knowledge, and mechanical principles. This paper presents a set of AI design techniques for building structures based on two types of generative AI: generative adversarial networks and graph neural networks. Specifically, these techniques effectively master the design of vertical and horizontal component layouts as well as the cross-sectional size of components in reinforced concrete shear walls and frame structures of tall buildings. Consequently, these approaches enable the development of high-quality and high-efficiency AI designs for building structures.

• ETRI Journal
• /
• 제44권6호
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.

• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2096-2106
• /
• 2023

Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.

• 한국수자원학회논문집
• /
• 제56권8호
• /
• pp.471-484
• /
• 2023

적대적 생성 신경망 기반의 딥러닝 모델은 학습된 정보를 바탕으로 새로운 정보를 생성하는데 특화되어 있다. 구글 딥마인드에서 개발한 deep generative model of rain (DGMR) 모델은 대규모 레이더 이미지 데이터의 복잡한 패턴과 관계를 학습하여, 예측 레이더 이미지를 생성하는 적대적 생성 신경망 모델이다. 본 연구에서는 환경부 레이더 강우관측자료를 이용하여 DGMR 모델을 학습하고, 2021년 8월 호우사례를 대상으로 적대적 생성 신경망을 이용하여 강우예측을 수행하고 기존 예측기법들과 정확도를 비교하였다. DGMR은 대체적으로 선행 60분까지는 강우 분포 위치가 관측강우와 가장 유사하였으나, 전체 영역에서 강한 강우가 발생한 사례에서는 강우가 지속적으로 발달하는 것으로 예측하는 경향이 있었다. 통계적 평가에서도 DGMR 기법이 1시간 선행예측에서 임계성공지수 0.57~0.79, 평균절대오차 0.57~1.36 mm로 나타나 타 기법 대비 효과적인 강우예측 기법임을 보여주었다. 다만, 생성 결과의 다양성이 부족한 경우가 발생하여 예측 정확도를 저하하므로 다양성을 개선하기 위한 연구와 2시간 이상의 선행예측에 대한 정확도 개선을 위해 물리기반 수치예보모델 예측강우 자료를 이용한 보완이 필요할 것으로 판단되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• 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.

• Journal of Semiconductor Engineering
• /
• 제2권1호
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.1-13
• /
• 2021

In this research, we study the problem of font image skeletonization using an end-to-end deep adversarial network, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies have been concerned with skeletonization, but a few have utilized deep learning. Further, no study has considered generative models based on deep neural networks for font character skeletonization, which are more delicate than natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of font characters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization, in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generator is proved superior to all well-known mathematical skeletonization methods in terms of character structure, including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominance of our method against the state-of-the-art supervised image-to-image translation method in font character skeletonization task.