• 한국산업정보학회논문지
• /
• 제29권2호
• /
• pp.35-45
• /
• 2024

본 논문에서는 CNN과 Attention 기법을 통한 깊이 영상의 화면 내 예측 방법을 제안한다. 제안하는 방법을 통해 예측하고자 하는 블록 내 화소마다 참조 화소를 선택할 수 있도록 한다. CNN을 통해 예측 블록의 상단과 좌단에서 각각 수직방향과 수평 방향의 공간적 특징을 검출한다. 두 공간적 특징은 예측블록과 참조 화소들에 대한 특징을 예측하기 위해 각각 특징차원과 공간적 차원으로 병합된다. Attention을 통해 예측 블록과 참조 화소간의 상관성을 입력된 공간적 특징을 통해 예측한다. Attention을 통해 예측된 상관성은 CNN 레이어를 통해 화소 도메인으로 복원되어 블록 내 화소 값이 예측된다. 제안된 방법이 VVC의 인트라 모드에 추가되었을 때 화면 예측 오차가 평균 5.8% 감소하였다.

• 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.

• Journal of Information Processing Systems
• /
• 제19권1호
• /
• pp.98-108
• /
• 2023

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2022년도 하계학술대회
• /
• pp.1311-1314
• /
• 2022

DNN을 사용하여 객체 인식 과정에서 객체를 잘 분류하기 위해서는 시각적 설명성이 요구된다. 시각적 설명성은 object class에 대한 예측을 pixel-wise attribution으로 표현해 예측 근거를 해석하기 위해 제안되었다, Scale-invariant한 특징을 제공하도록 설계된 pyramidal features 기반 backbone 구조는 object detection 및 classification 등에서 널리 쓰이고 있으며, 이러한 특징을 갖는 feature pyramid를 trainable attention mechanism에 적용하고자 할 때 계산량 및 메모리의 복잡도가 증가하는 문제가 있다. 본 논문에서는 일반적인 FPN에서 객체 인식 성능과 설명성을 높이기 위한 피라미드-주의집중 계층네트워크 (FPN-Attention Layered Network) 방식을 제안하고, 실험적으로 그 특성을 평가하고자 한다. 기존의 FPN만을 사용하였을 때 객체 인식 과정에서 설명성을 향상시키는 방식이 객체 인식에 미치는 정도를 정량적으로 평가하였다. 제안된 모델의 적용을 통해 낮은 computing 오버헤드 수준에서 multi-level feature를 고려한 시각적 설명성을 개선시켜, 결괴적으로 객체 인식 성능을 향상 시킬 수 있음을 실험적으로 확인할 수 있었다.

• Journal of Information Processing Systems
• /
• 제18권1호
• /
• pp.59-74
• /
• 2022

During the last decade, the security of digital images has received considerable attention in various multimedia transmission schemes. However, many current cryptosystems tend to adopt a single-layer permutation or diffusion algorithm, resulting in inadequate security. A hierarchical bilateral diffusion architecture for color image encryption is proposed in response to this issue, based on a hyperchaotic system and DNA sequence operation. Primarily, two hyperchaotic systems are adopted and combined with cipher matrixes generation algorithm to overcome exhaustive attacks. Further, the proposed architecture involves designing pixelpermutation, pixel-diffusion, and DNA (deoxyribonucleic acid) based block-diffusion algorithm, considering system security and transmission efficiency. The pixel-permutation aims to reduce the correlation of adjacent pixels and provide excellent initial conditions for subsequent diffusion procedures, while the diffusion architecture confuses the image matrix in a bilateral direction with ultra-low power consumption. The proposed system achieves preferable number of pixel change rate (NPCR) and unified average changing intensity (UACI) of 99.61% and 33.46%, and a lower encryption time of 3.30 seconds, which performs better than some current image encryption algorithms. The simulated results and security analysis demonstrate that the proposed mechanism can resist various potential attacks with comparatively low computational time consumption.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.15-29
• /
• 2024

A fetoscope is an optical endoscope, which is often applied in fetoscopic laser photocoagulation to treat twin-to-twin transfusion syndrome. In an operation, the clinician needs to observe the abnormal placental vessels through the endoscope, so as to guide the operation. However, low-quality imaging and narrow field of view of the fetoscope increase the difficulty of the operation. Introducing an accurate placental vessel segmentation of fetoscopic images can assist the fetoscopic laser photocoagulation and help identify the abnormal vessels. This study proposes a method to solve the above problems. A novel encoder-decoder network with a dual-path structure is proposed to segment the placental vessels in fetoscopic images. In particular, we introduce a channel attention mechanism and a continuous convolution structure to obtain multi-scale features with their weights. Moreover, a switching connection is inserted between the corresponding blocks of the two paths to strengthen their relationship. According to the results of a set of blood vessel segmentation experiments conducted on a public fetoscopic image dataset, our method has achieved higher scores than the current mainstream segmentation methods, raising the dice similarity coefficient, intersection over union, and pixel accuracy by 5.80%, 8.39% and 0.62%, respectively.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제48권12호
• /
• pp.761-767
• /
• 1999

Poly-Si TFTs(polycrystalline silicon thin film transistors) fabricated on a low cost glass substrate have attracted a considerable amount of attention for pixel elements and peripheral driving circuits in AMLCS(active matrix liquid crystal display). In order to apply poly-Si TFTs for high resolution AMLCD, a high operating frequency and reliable circuit performances are desired. A new poly-Si TFT with CLBT(counter doped lateral body terminal) is proposed and fabricated to suppress kink effects and to improve the device stability. And this proposed device with BC(buried channel) is fabricated to increase ON-current and operating frequency. Although the troublesome LDD structure is not used in the proposed device, a low OFF-current is successfully obtained by removing the minority carrier through the CLBT. We have measured the dynamic properties of the poly-Si TFT device and its circuit. The reliability of the TFTs and their circuits after AC stress are also discussed in our paper. Our experimental results show that the BC enables the device to have high mobility and switching frequency (33MHz at $V_{DD}$ = 15 V). The minority carrier elimination of the CLBT suppresses kink effects and makes for superb dynamic reliability of the CMOS circuit. We have analyzed the mechanism in order to see why the ring oscillators do not operate by analyzing AC stressed device characteristics.