• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.524-530
• /
• 2023

This paper proposes an efficient algorithm to detect CAN (Controller Area Network) bus attack based on a lightweight CNN (Convolutional Neural Network), and an IDS(Intrusion Detection System) was designed, implemented, and verified with FPGA. Compared to conventional CNN-based IDS, the proposed IDS detects CAN bus attack on a frame-by-frame basis, enabling accurate and rapid response. Furthermore, the proposed IDS can significantly reduce hardware since it exploits only one convolutional layer, compared to conventional CNN-based IDS. Simulation and implementation results show that the proposed IDS effectively detects various attacks on the CAN bus.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.840-860
• /
• 2023

Aiming at the serious occlusion and slow tracking speed in pedestrian target tracking and recognition in complex scenes, a target tracking method based on improved YOLO v5 combined with Deep SORT is proposed. By merging the attention mechanism ECA-Net with the Neck part of the YOLO v5 network, using the CIoU loss function and the method of CIoU non-maximum value suppression, connecting the Deep SORT model using Shuffle Net V2 as the appearance feature extraction network to achieve lightweight and fast speed tracking and the purpose of improving tracking under occlusion. A large number of experiments show that the improved YOLO v5 increases the average precision by 1.3% compared with other algorithms. The improved tracking model, MOTA reaches 54.3% on the MOT17 pedestrian tracking data, and the tracking accuracy is 3.7% higher than the related algorithms and The model presented in this paper improves the FPS by nearly 5 on the fps indicator.

• Convergence Security Journal
• /
• v.15 no.4
• /
• pp.35-41
• /
• 2015

Internet of Things has a wide range of vulnerabilities are exposed to information security threats. However, this does not deal with the basic solution, the vaccine does not secure encryption for the data transmission. The encryption and authentication message transmitted from one node to the construction of the secure wireless sensor networks is required. In order to satisfy the constraint, and security requirements of the sensor network, lightweight encryption and authentication technologies, the light key management technology for the sensor environment it is required. Mandatory sensor network security technology, privacy protection technology subchannel attack prevention, and technology. In order to establish a secure wireless sensor networks encrypt messages sent between the nodes and it is important to authenticate. Lightweight it shall apply the intrusion detection mechanism functions to securely detect the presence of the node on the network. From the sensor node is not involved will determine the authenticity of the terminal authentication technologies, there is a need for a system. Network security technology in an Internet environment objects is a technique for enhancing the security of communication channel between the devices and the sensor to be the center.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5442-5463
• /
• 2016

Designing efficient routing protocols for a wireless sensor network with mobile sinks (mWSN) is a challenging task since the network topology and data paths change frequently as sink nodes move. In this paper, we design a novel lightweight reactive ring based routing protocol called R3, which removes the need of proactively maintaining data paths to mobile sinks as they move in the network. To achieve high packet delivery ratio and low transmission cost, R3 combines ring based forwarding and trail based forwarding together. To support efficient ring based forwarding, we build a ring based structure for a network in a way such that each node in the network can easily obtain its ring ID and virtual angle information. For this purpose, we artificially create a virtual hole in the central area of the network and accordingly find a shortest cycled path enclosing the hole, which serves as base ring and is used for generating the remaining ring based structure. We accordingly present the detailed design description for R3, which only requires each node to keep very limited routing information. We derive the communication overhead by ring based forwarding. Extensive simulation results show that R3 can achieve high routing performance as compared with existing work.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.10
• /
• pp.103-108
• /
• 2016

With the growing trend of pervasive computing, (the idea that technology is moving beyond personal computers to everyday devices) there is a growing demand for lightweight ciphers to safeguard data in a network that is always available. For all block cipher applications, the AES is the preferred choice. However, devices used in pervasive computing have extremely constraint environment and as such the AES will not be suitable. In this paper we design and implement a new lightweight compact block cipher that takes advantage of both S-P network and the Feistel structure. The cipher uses the S-box of PRESENT algorithm and a key dependent one stage omega permutation network is used as the cipher's P-box. The cipher is implemented on iNEXT-V6 board equipped with virtex-6 FPGA. The design synthesized to 196 slices at 337 MHz maximum clock frequency.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.778-789
• /
• 2021

Recently, various lightweight methods for using Convolutional Neural Network(CNN) models in mobile devices have emerged. Weight quantization, which lowers bit precision of weights, is a lightweight method that enables a model to be used through integer calculation in a mobile environment where GPU acceleration is unable. Weight quantization has already been used in various models as a lightweight method to reduce computational complexity and model size with a small loss of accuracy. Considering the size of memory and computing speed as well as the storage size of the device and the limited network environment, this paper proposes a method of compressing integer weights after quantization using a video codec as a method. To verify the performance of the proposed method, experiments were conducted on VGG16, Resnet50, and Resnet18 models trained with ImageNet and Places365 datasets. As a result, loss of accuracy less than 2% and high compression efficiency were achieved in various models. In addition, as a result of comparison with similar compression methods, it was verified that the compression efficiency was more than doubled.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.12
• /
• pp.5150-5169
• /
• 2015

Mobile Ad hoc NETworks (MANETs) are the best choice when mobility, scalability, and decentralized network infrastructure are needed. Because of critical mission applications of MANETs, network security is the vital requirement. Most routing protocols in MANETs assume that every node in the network is trustworthy. However, due to the open medium, the wide distribution, and the lack of nodes' physical protection, attackers can easily compromise MANETs by inserting misbehaving nodes into the network that make blackhole attacks. Previous research to detect the misbehaving nodes in MANETs used the overhearing methods, or additional ACKnowledgement (ACK) packets to confirm the reception of data packets. In this paper a special lightweight acknowledgement-based method is developed that, contrary to existing methods, it uses ACK packets of MAC layer instead of adding new ACK packets to the network layer for confirmations. In fact, this novel method, named PIGACK, uses ACK packets of MAC 802.11 to piggyback confirmations from a receiver to a sender in the same transmission duration that the sender sends a data packet to the receiver. Analytical and simulation results show that the proposed method considerably decreases the network overhead and increases the packet delivery ratio compared to the well-known method (2ACK).