• International journal of advanced smart convergence
• /
• v.10 no.3
• /
• pp.163-171
• /
• 2021

Recently, Machine Learning-based visualization approaches have been proposed to combat the problem of malware detection. Unfortunately, these techniques are exposed to Adversarial examples. Adversarial examples are noises which can deceive the deep learning based malware detection network such that the malware becomes unrecognizable. To address the shortcomings of these approaches, we present Block-matching and 3D filtering (BM3D) algorithm and deep image prior based denoising technique to defend against adversarial examples on visualization-based malware detection systems. The BM3D based denoising method eliminates most of the adversarial noise. After that the deep image prior based denoising removes the remaining subtle noise. Experimental results on the MS BIG malware dataset and benign samples show that the proposed denoising based defense recovers the performance of the adversarial attacked CNN model for malware detection to some extent.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.534-537
• /
• 2009

Clustering protocol of Wireless sensor networks(WSNs) can not only reduce the volume of inter-node communication by the nodes's data aggregation but also extend the nodes's sleep times by cluster head's TDMA-schedule coordination. In order to extend the network lifetime of WSNs, we propose CHS algorithm to select cluster-head using three variables. It consists of initial and current energy of nodes, round information, and total numbers which have been selected as cluster head until current round.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.789-792
• /
• 2009

As RFID technology is becoming ubiquitous, the secunty of these systems gets much attention. Its fields of usage include personal identification, supply-chain management systems, and many more. Many kinds of RFID tags are available on the market which differ both in storage, and computational capacity. Since by standard IT means all the tags have small capacities, the security mechanisms which are in use in computer networks are not suitable. For expensive tags with relatively large computational capacities many secure communication protocols were developed, for cheap low-end tags, only a few lightweight protocols exist. In this paper we introduce our solution, which is based on the least computation demanding operator, the exclusive or function. By introducing two tags instead of one in the RFID system, our scheme provides security solutions which are comparable with those provided by the lightweight protocols. In the meantime, our scheme does not demand any computational steps to be made by the ta.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.749-751
• /
• 2009

In this paper, we designed a sensor network using zigbee for controlling and monitoring semiconductor equipments. Unlike general kinds of sensor networks, it is important to preferential send emergency data to the control server. Therefore, we proposed a MAC protocol which consider the priority for the urgency data handling.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.14 no.2
• /
• pp.69-74
• /
• 2004

Threshold digital signature is very useful for networks that have no infrastructure such as ad hoc network Up to date, research on threshold digital signature is mainly focused on RSA and DSA. Though Schnorr's digital signature scheme is very efficient in terms of both computation and communication. its hard structure using interactive proof prevents conversion to threshold version. This paper proposes an efficient threshold signature. scheme based on the Schnorr's signature. It has a desirable property of scalability and reduces runtime costs by precomputation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4595-4610
• /
• 2020

In the practical communication environment, the accurate channel state information (CSI) is difficult to obtain, which will cause the mismatch of resource and degrade the system performance. In this paper, to account for the channel uncertainties, a robust power allocation scheme for a downlink Non-orthogonal multiple access (NOMA) heterogeneous network (HetNet) is designed to maximize energy efficiency (EE), which can ensure the quality of service (QoS) of users. We conduct the robust optimization model based on worse-case method, in which the channel gains belong to certain ellipsoid sets. To solve the non-convex non-liner optimization, we transform the optimization problem via Dinkelbach method and sequential convex programming, and the power allocation of small cell users (SCUs) is achieved by Lagrange dual approach. Finally, we analysis the convergence performance of proposed scheme. The simulation results demonstrate that the proposed algorithm can improve total EE of SCUs, and has a fast convergence performance.

• Electronics and Telecommunications Trends
• /
• v.36 no.4
• /
• pp.34-47
• /
• 2021

To realize remote surgery from hundreds of kilometers away, a new communication environment with ultra-low latency and high-precision features is required. Thus, ultra-high precision networking technology that guarantees the maximum latency and jitter of end-to-end traffic on an Internet-scale wide area network is in development as part of 6G network research. This paper describes the current status of various networking technologies in ITU-T, ETSI, IEEE, and IETF to ensure ultra-low latency and high precision in wired networks.

• ETRI Journal
• /
• v.43 no.1
• /
• pp.82-94
• /
• 2021

In this work, six voiced/unvoiced speech classifiers based on the autocorrelation function (ACF), average magnitude difference function (AMDF), cepstrum, weighted ACF (WACF), zero crossing rate and energy of the signal (ZCR-E), and neural networks (NNs) have been simulated and implemented in real time using the TMS320C6713 DSP starter kit. These speech classifiers have been integrated into a linear-predictive-coding-based speech analysis-synthesis system and their performance has been compared in terms of the percentage of the voiced/unvoiced classification accuracy, speech quality, and computation time. The results of the percentage of the voiced/unvoiced classification accuracy and speech quality show that the NN-based speech classifier performs better than the ACF-, AMDF-, cepstrum-, WACF- and ZCR-E-based speech classifiers for both clean and noisy environments. The computation time results show that the AMDF-based speech classifier is computationally simple, and thus its computation time is less than that of other speech classifiers, while that of the NN-based speech classifier is greater compared with other classifiers.

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.209-214
• /
• 2020

VoIP technology has been widely used for exchanging voice or image data through IP networks. VoIP technology, often called Internet Telephony, sends and receives voice data over the RTP protocol during the session. However, there is an exposition risk in the voice data in VoIP using the RTP protocol, where the RTP protocol does not have a specification for encryption of the original data. We implement programs that can extract meaningful information from the user's dialogue. The meaningful information means the information that the program user wants to obtain. In order to do that, our implementation has two parts. One is the client part, which inputs the keyword of the information that the user wants to obtain, and the other is the server part, which sniffs and performs the speech recognition process. We use the Google Speech API from Google Cloud, which uses machine learning in the speech recognition process. Finally, we discuss the usability and the limitations of the implementation with the example.

• Journal of information and communication convergence engineering
• /
• v.19 no.1
• /
• pp.22-28
• /
• 2021

Convolutional neural networks (CNNs) are one of the most frequently used artificial intelligence techniques. Among CNN-based applications, small and timing-sensitive applications have emerged, which must be reliable to prevent severe accidents. However, as the small and timing-sensitive systems do not have sufficient system resources, they do not possess proper error protection schemes. In this paper, we propose MATE, which is a low-cost CNN weight error correction technique. Based on the observation that all mantissa bits are not closely related to the accuracy, MATE replaces some mantissa bits in the weight with error correction codes. Therefore, MATE can provide high data protection without requiring additional memory space or modifying the memory architecture. The experimental results demonstrate that MATE retains nearly the same accuracy as the ideal error-free case on erroneous DRAM and has approximately 60% accuracy, even with extremely high bit error rates.