• Title/Summary/Keyword: 적대적 훈련

Search Result 27, Processing Time 0.029 seconds

전자시대의 개인휴대장비

  • Jeong, Bong-Hyeon
    • Defense and Technology
    • /
    • no.3 s.97
    • /
    • pp.23-27
    • /
    • 1987
  • 지휘관 및 병사 공히 새로운 기술을 받아들이는데 신중하고 너무 늦었던 예가 역사상에 많이 있다. 우리들은 규로 전자공학에 기초를 두고 기술혁신을 체험하고 있다. 이들은 통신, 자기위치측정, 적대적, 목표위치판정, 정보축적의 분야로 나날이 변화하고 있다. 또한 이들의 성능을 개발하는데 따라 정보자료수집을 위한 기술로 개발되어 사용된다. 전자공학기술은 개발되고 있으나 지휘관이나 병사는 "이러한 장비를 여하히 사용하겠는가" "이러한 기술을 전술에 여하히 연결시키는가" 를 교육하기 위한 훈련체계의 부족이 중요한 문제가 되고 있다. 비스마르크함상에 레이다탐지기를 설치하였으나 레이다로 군함을 보호할 수가 없었다. 지휘관이 레이다에 탐지되지 않았던 시에 상대에게 탐지되었다고 믿었기 때문이다.

  • PDF

Study on the Vulnerabilities of Automatic Speech Recognition Models in Military Environments (군사적 환경에서 음성인식 모델의 취약성에 관한 연구)

  • Elim Won;Seongjung Na;Youngjin Ko
    • Convergence Security Journal
    • /
    • v.24 no.2
    • /
    • pp.201-207
    • /
    • 2024
  • Voice is a critical element of human communication, and the development of speech recognition models is one of the significant achievements in artificial intelligence, which has recently been applied in various aspects of human life. The application of speech recognition models in the military field is also inevitable. However, before artificial intelligence models can be applied in the military, it is necessary to research their vulnerabilities. In this study, we evaluates the military applicability of the multilingual speech recognition model "Whisper" by examining its vulnerabilities to battlefield noise, white noise, and adversarial attacks. In experiments involving battlefield noise, Whisper showed significant performance degradation with an average Character Error Rate (CER) of 72.4%, indicating difficulties in military applications. In experiments with white noise, Whisper was robust to low-intensity noise but showed performance degradation under high-intensity noise. Adversarial attack experiments revealed vulnerabilities at specific epsilon values. Therefore, the Whisper model requires improvements through fine-tuning, adversarial training, and other methods.

A Study of GAN-based data augmentation technique on Acceleration Data Gereration (GAN 기반 데이터 증강기법을 통한 가속도 데이터 생성에 대한 연구)

  • Kang, Sung-Hwan;Chow, We-Duke
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2022.07a
    • /
    • pp.495-497
    • /
    • 2022
  • 본 데이터 GAN 기법 데이터 증강기법을 적용하여 가속도 데이터를 증강하는 방법에 대해 연구한다. 가속도 데이터는 사람의 활동패턴을 인지하는데 있어 가장 기본적인 데이터로 활용된다. 가속도 데이터를 증강한 뒤, 활동패턴을 인지하는 머신러닝 모델 훈련에 사용한 결과 생성한 데이터가 육안으로 확인하였을 때 실제 데이터와 유사한 패턴을 형성하였고, 실제 활동패턴인지 모델 훈련에 사용한 결과 정확도(Accuracy)는 기존 데이터로만 훈련한 경우 74%인데 비해 증강된 데이터를 혼합하여 훈련하였을 때 약 88%로 개선된 것을 확인하였다.

  • PDF

Application of transfer learning to develop radar-based rainfall prediction model with GAN(Generative Adversarial Network) for multiple dam domains (다중 댐 유역에 대한 강우예측모델 개발을 위한 전이학습 기법의 적용)

  • Choi, Suyeon;Kim, Yeonjoo
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2022.05a
    • /
    • pp.61-61
    • /
    • 2022
  • 최근 머신러닝 기술의 발달에 따라 이를 활용한 레이더 자료기반 강우예측기법이 활발히 개발되고 있다. 기존 머신러닝을 이용한 강우예측모델 개발 관련 연구는 주로 한 지역에 대해 수행되며, 데이터 기반으로 훈련되는 머신러닝 기법의 특성상 개발된 모델이 훈련된 지역에 대해서만 좋은 성능을 보인다는 한계점이 존재한다. 이러한 한계점을 해결하기 위해 사전 훈련된 모델을 이용하여 새로운 데이터에 대해 모델을 훈련하는 전이학습 기법 (transfer learning)을 적용하여 여러 유역에 대한 강우예측모델을 개발하고자 하였다. 본 연구에서는 사전 훈련된 강우예측 모델로 생성적 적대 신경망 기반 기법(Generative Adversarial Network, GAN)을 이용한 미래 강우예측모델을 사용하였다. 해당 모델은 기상청에서 제공된 2014년~2017년 여름의 레이더 이미지 자료를 이용하여 초단기, 단기 강우예측을 수행하도록 학습시켰으며, 2018년 레이더 이미지 자료를 이용한 단기강우예측 모의에서 좋은 성능을 보였다. 본 연구에서는 훈련된 모델을 이용해 새로운 댐 유역(안동댐, 충주댐)에 대한 강우예측모델을 개발하기 위해 여러 전이학습 기법을 적용하고, 그 결과를 비교하였다. 결과를 통해 새로운 데이터로 처음부터 훈련시킨 모델보다 전이학습 기법을 사용하였을 때 좋은 성능을 보이는 것을 확인하였으며, 이를 통해 여러 댐 유역에 대한 모델 개발 시 전이학습 기법이 효율적으로 적용될 수 있음을 확인하였다.

  • PDF

Adversarial Framework for Joint Light Field Super-resolution and Deblurring (라이트필드 초해상도와 블러 제거의 동시 수행을 위한 적대적 신경망 모델)

  • Lumentut, Jonathan Samuel;Baek, Hyungsun;Park, In Kyu
    • Journal of Broadcast Engineering
    • /
    • v.25 no.5
    • /
    • pp.672-684
    • /
    • 2020
  • Restoring a low resolution and motion blurred light field has become essential due to the growing works on parallax-based image processing. These tasks are known as light-field enhancement process. Unfortunately, only a few state-of-the-art methods are introduced to solve the multiple problems jointly. In this work, we design a framework that jointly solves light field spatial super-resolution and motion deblurring tasks. Particularly, we generate a straight-forward neural network that is trained under low-resolution and 6-degree-of-freedom (6-DOF) motion-blurred light field dataset. Furthermore, we propose the strategy of local region optimization on the adversarial network to boost the performance. We evaluate our method through both quantitative and qualitative measurements and exhibit superior performance compared to the state-of-the-art methods.

Anomaly Detection for User Action with Generative Adversarial Networks (적대적 생성 모델을 활용한 사용자 행위 이상 탐지 방법)

  • Choi, Nam woong;Kim, Wooju
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.3
    • /
    • pp.43-62
    • /
    • 2019
  • At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

Semantic Object Segmentation Using Conditional Generative Adversarial Network with Residual Connections (잔차 연결의 조건부 생성적 적대 신경망을 사용한 시맨틱 객체 분할)

  • Ibrahem, Hatem;Salem, Ahmed;Yagoub, Bilel;Kang, Hyun Su;Suh, Jae-Won
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.12
    • /
    • pp.1919-1925
    • /
    • 2022
  • In this paper, we propose an image-to-image translation approach based on the conditional generative adversarial network for semantic segmentation. Semantic segmentation is the task of clustering parts of an image together which belong to the same object class. Unlike the traditional pixel-wise classification approach, the proposed method parses an input RGB image to its corresponding semantic segmentation mask using a pixel regression approach. The proposed method is based on the Pix2Pix image synthesis method. We employ residual connections-based convolutional neural network architectures for both the generator and discriminator architectures, as the residual connections speed up the training process and generate more accurate results. The proposed method has been trained and tested on the NYU-depthV2 dataset and could achieve a good mIOU value (49.5%). We also compare the proposed approach to the current methods in semantic segmentation showing that the proposed method outperforms most of those methods.

Adversarial Shade Generation and Training Text Recognition Algorithm that is Robust to Text in Brightness (밝기 변화에 강인한 적대적 음영 생성 및 훈련 글자 인식 알고리즘)

  • Seo, Minseok;Kim, Daehan;Choi, Dong-Geol
    • The Journal of Korea Robotics Society
    • /
    • v.16 no.3
    • /
    • pp.276-282
    • /
    • 2021
  • The system for recognizing text in natural scenes has been applied in various industries. However, due to the change in brightness that occurs in nature such as light reflection and shadow, the text recognition performance significantly decreases. To solve this problem, we propose an adversarial shadow generation and training algorithm that is robust to shadow changes. The adversarial shadow generation and training algorithm divides the entire image into a total of 9 grids, and adjusts the brightness with 4 trainable parameters for each grid. Finally, training is conducted in a adversarial relationship between the text recognition model and the shaded image generator. As the training progresses, more and more difficult shaded grid combinations occur. When training with this curriculum-learning attitude, we not only showed a performance improvement of more than 3% in the ICDAR2015 public benchmark dataset, but also confirmed that the performance improved when applied to our's android application text recognition dataset.

Comparison of CNN and GAN-based Deep Learning Models for Ground Roll Suppression (그라운드-롤 제거를 위한 CNN과 GAN 기반 딥러닝 모델 비교 분석)

  • Sangin Cho;Sukjoon Pyun
    • Geophysics and Geophysical Exploration
    • /
    • v.26 no.2
    • /
    • pp.37-51
    • /
    • 2023
  • The ground roll is the most common coherent noise in land seismic data and has an amplitude much larger than the reflection event we usually want to obtain. Therefore, ground roll suppression is a crucial step in seismic data processing. Several techniques, such as f-k filtering and curvelet transform, have been developed to suppress the ground roll. However, the existing methods still require improvements in suppression performance and efficiency. Various studies on the suppression of ground roll in seismic data have recently been conducted using deep learning methods developed for image processing. In this paper, we introduce three models (DnCNN (De-noiseCNN), pix2pix, and CycleGAN), based on convolutional neural network (CNN) or conditional generative adversarial network (cGAN), for ground roll suppression and explain them in detail through numerical examples. Common shot gathers from the same field were divided into training and test datasets to compare the algorithms. We trained the models using the training data and evaluated their performances using the test data. When training these models with field data, ground roll removed data are required; therefore, the ground roll is suppressed by f-k filtering and used as the ground-truth data. To evaluate the performance of the deep learning models and compare the training results, we utilized quantitative indicators such as the correlation coefficient and structural similarity index measure (SSIM) based on the similarity to the ground-truth data. The DnCNN model exhibited the best performance, and we confirmed that other models could also be applied to suppress the ground roll.

Sparse Class Processing Strategy in Image-based Livestock Defect Detection (이미지 기반 축산물 불량 탐지에서의 희소 클래스 처리 전략)

  • Lee, Bumho;Cho, Yesung;Yi, Mun Yong
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.11
    • /
    • pp.1720-1728
    • /
    • 2022
  • The industrial 4.0 era has been opened with the development of artificial intelligence technology, and the realization of smart farms incorporating ICT technology is receiving great attention in the livestock industry. Among them, the quality management technology of livestock products and livestock operations incorporating computer vision-based artificial intelligence technology represent key technologies. However, the insufficient number of livestock image data for artificial intelligence model training and the severely unbalanced ratio of labels for recognizing a specific defective state are major obstacles to the related research and technology development. To overcome these problems, in this study, combining oversampling and adversarial case generation techniques is proposed as a method necessary to effectively utilizing small data labels for successful defect detection. In addition, experiments comparing performance and time cost of the applicable techniques were conducted. Through experiments, we confirm the validity of the proposed methods and draw utilization strategies from the study results.