• Journal of Korea Multimedia Society
• /
• v.11 no.10
• /
• pp.1347-1358
• /
• 2008

A blind video watermarking scheme for providing safety, authenticity, and copyright protection is proposed in this paper, which is robust to MPEG-4 SVC and multimedia transcoding. In proposed method, embedding and detecting of watermark is performed based on base layer with considering spatial SVC. To be robust from temporal SVC, our method embeds repeatedly a permutated character with ordering number per one frame. Also for robustness from multimedia transcoding and FGS, the method is embedded watermark in low middle frequency of each frame adaptively based on DCT in ROI. Through experimental results, invisibility of the watermark is confirmed and robustness of the watermark against the spatial SVC, temporal SVC, FGS and video transcoding between MPEG-2 and MPEG-4 SVC is also verified.

• The KIPS Transactions:PartC
• /
• v.13C no.1 s.104
• /
• pp.55-62
• /
• 2006

It is growing to use the E-Commerce, recently However, if a cracking tool that detects e keyboard input is set up, users' input values and personal information could be taken away. This paper shows the design and implementation of security system that prevent the keyboard input information leaking. The ideas of thus paper are encrypting the keyboard input values with using the keyboard interrupt hooking, the browser embedding program's decrypting the values in case of need and decrypting all values in the web server. The own input control was developed for direct attacks to the browser, and that the values of password fields which are showed as *(asterisk character) won't be decrypted in the client PC is different from other commercial keyboard input security systems. Consequently, this paper shows the chance of realizing a lot safer customer information protective system than before.

• Journal of Korea Multimedia Society
• /
• v.9 no.5
• /
• pp.624-634
• /
• 2006

This paper presents a new watermarking scheme that is robust against geometrical attacks such as translation and rotation. The proposed method is based on the conventional PSADT(Polar Coordinates Shape Adaptive Discrete Transform) method which is an robust watermarking scheme for an arbitrarily-shaped image such as character images. The PSADT method shows perfect robustness against geometrical attack if there is no change in the shape of the image object. However, it cannot be utilized to watermark general rectangular images because of the missing alignment between the watermarked signals in the embedding and extracting side. To overcome this problem we propose a new watermarking scheme that aligns the watermark signal using the image inherent feature, especially corner. Namely the proposed method decides a consistent target region whose shape and position isn't changed by any malicious attack and then embeds the watermark in it using the PSADT method. Experimental results show the robustness of the proposed method against geometrical attacks as well as image compression.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.11
• /
• pp.66-78
• /
• 2015

With the development of bio computing technology, DNA watermarking to do as a medium of DNA information has been researched in the latest time. However, DNA information is very important in biologic function unlikely multimedia data. Therefore, the reversible DNA watermarking is required for the host DNA information to be perfectively recovered. This paper presents a reversible DNA watermarking using least square based prediction error expansion for noncodng DNA sequence. Our method has three features. The first thing is to encode the character string (A,T,C,G) of nucleotide bases in noncoding region to integer code values by grouping n nucleotide bases. The second thing is to expand the prediction error based on least square (LS) as much as the expandable bits. The last thing is to prevent the false start codon using the comparison searching of adjacent watermarked code values. Experimental results verified that our method has more high embedding capacity than conventional methods and mean prediction method and also makes the prevention of false start codon and the preservation of amino acids.

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.47-52
• /
• 2018

Named Entity Recognition is a system that extracts entity names such as Persons(PS), Locations(LC), and Organizations(OG) that can have a unique meaning from a document and determines the categories of extracted entity names. Recently, Bi-LSTM-CRF, which is a combination of CRF using the transition probability between output data from LSTM-based Bi-LSTM model considering forward and backward directions of input data, showed excellent performance in the study of object name recognition using deep-learning, and it has a good performance on the efficient embedding vector creation by character and word unit and the model using CNN and LSTM. In this research, we describe the Bi-LSTM-CNN-CRF model that enhances the features of the Korean named entity recognition system and propose a method for constructing the traditional culture corpus. We also present the results of learning the constructed corpus with the feature augmentation model for the recognition of Korean object names.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.12
• /
• pp.67-75
• /
• 2016

DNA computing technology makes the interests on DNA storage and DNA watermarking / steganography that use the DNA information as a newly medium. DNA watermarking that embeds the external watermark into DNA information without the biological mutation needs the reversibility for the perfect recovery of host DNA, the continuous embedding and detecting processing, and the mutation analysis by the watermark. In this paper, we propose a reversible DNA watermarking based on circular histogram shifting of DNA code values with the prevention of false start codon, the preservation of DNA sequence length, and the high watermark capacity, and the blind detection. Our method has the following features. The first is to encode nucleotide bases of 4-character variable to integer code values by code order. It makes the signal processing of DNA sequence easy. The second is to embed the multiple bits of watermark into -order coded value by using circular histogram shifting. The third is to check the possibility of false start codon in the inter or intra code values. Experimental results verified the our method has higher watermark capacity 0.11~0.50 bpn than conventional methods and also the false start codon has not happened in our method.