• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.878-883
• /
• 2020

Cryptographic algorithms are used to prevent the illegal manipulation of data. They are divided into public-key cryptosystems and symmetric-key cryptosystems. Public-key cryptosystems require considerable time for encryption and decryption compared to symmetric-key cryptosystem. On the other hand, key management, and delivery are easier for public-key cryptosystems than symmetric-key cryptosystems because different keys are used for encryption and decryption. Furthermore, hash functions are being used very effectively to verify the integrity of the digital content, as they always generate output with a fixed size using the data of various sizes as input. This paper proposes a method using RSA public-key cryptography and a hash function to determine if a digital image is deformed or not and to detect the manipulated location. In the proposed method, the entire image is divided into several blocks, 64×64 in size. The watermark is then allocated to each block to verify the deformation of the data. When deformation occurs, the manipulated pixel will be divided into smaller 4×4 sub-blocks, and each block will have a watermark to detect the location. The safety of the proposed method depends on the security of the cryptographic algorithm and the hash function.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.11
• /
• pp.3576-3583
• /
• 2000

Digital watermarks have recently been proposed for the purposes of copyright ptotechtion and autheutication for multimedia contents. A watermarking technique consists of an algorithm that incorporates a watermarking structure into an image in the spatial or frequency domains. In this paper we proposed a new watermarking method for authentication and integrity of digital images and the proposed algorithm uses the MD5 hash funiction and a symmetric key encryption algorithm. To decide the position of embedding watermark and the bit pasitionin the original image, the secret key is used as an input of the MD5 hash function. The simulation results show that the proposed algorithm has the advantage of difficulty to find positions of inserted watermarks, and keep the similar watermarked image quabty with Wong's method.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.57-65
• /
• 2019

In this paper, we propose a Rights Management Information(RMI) expression systems for individual sites are integrated and the performance evaluation is performed to find out an efficient comparing and updating method of RMI through various image feature point search techniques. In addition, we proposed a weighted scoring model for both public domain sites and posts in order to use the most latest RMI based on reliable data. To solve problem that most public domain sites are exposed to copyright infringement by providing inconsistent RMI(Rights Management Information) expression system and non-up-to-date RMI information. The weighted scoring model proposed in this paper makes it possible to use the latest RMI for duplicated images that have been verified through the performance evaluation experiments of SIFT and CNN techniques and to improve the accuracy when applied to search engines. In addition, there is an advantage in providing users with accurate original public domain images and their RMI from the search engine even when some modified public domain images are searched by users.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.11
• /
• pp.196-201
• /
• 2016

Digital watermarking is a technique used to hide information within digital media. Digital watermarking techniques can be classified as either robust watermarking or fragile watermarking. Robust watermarking techniques are generally used for the purpose of copyright protection. In addition, fragile watermarking techniques are used for the authentication and integrity verification of a digital image. Therefore, fragile watermarks should be easily breakable for trivial tampering of a watermarked image. This paper proposes an efficient fragile watermarking method for image tamper detection in the spatial domain. In the proposed method, a hash code and symmetric key encryption algorithm are used. The proposed method of inserting a watermark by dividing the original image into many blocks of small sizes is not weak against attacks, such as cut and paste. The proposed method can detect the manipulated parts of a watermarked image without testing the entire block of the image.

• The KIPS Transactions:PartC
• /
• v.9C no.1
• /
• pp.1-8
• /
• 2002

Digital image watermarking is a technique for the purpose of protecting the ownership of the image by embedding proprietary watermarks in a digital image. It is required for the digital image watermarking scheme to pursue the robustness against water marking attacks and the perceptual Invisibility more than usual in steganography area, to guarantee not a hidden watermarking algorithm but the publicity of water-marking algorithm details and hidden use of key, which can protect the unauthorized user access from detection. In this paper we propose a new copyright watermarking scheme, which is barred on one-way hash functions using ElGamal functions and modular operations. ElGamal functions are widely used in cryptographic systems. Our watermarking scheme is robust against LSB(least significant bit) attacks and gamma correction attack, and also perceptually invisible. We demonstrate the characteristics of our proposed watermarking scheme through experiments. It is necessary to proceed as the future work the algorithm of achieving at the same time both the pseudo-randomness for the steno-key generation and the asymmetric-key generation.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.1-14
• /
• 2010

With the rapid growth of 3D content industry fields, 3D content-based hashing (or hash function) has been required to apply to authentication, trust and retrieval of 3D content. A content hash can be a random variable for compact representation of content. But 3D content-based hashing has been not researched yet, compared with 2D content-based hashing such as image and video. This paper develops a robust 3D content-based hashing based on key-dependent 3D surface feature. The proposed hashing uses the block surface coefficient using shape coordinate of 3D SSD and curvedness for 3D surface feature and generates a binary hash by a permutation key and a random key. Experimental results verified that the proposed hashing has the robustness against geometry and topology attacks and has the uniqueness of hash in each model and key.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.241-244
• /
• 2018

Domestic vehicle registration is continuously increasing every year, traffic accidents are also increasing by an increase in the number of vehicles. In the event of a traffic accident, the perpetrator and the victim should be judged and handled appropriately. When judging the accident situation, the black box is what evidence can be except for witness who is at the accident scene. The black box becomes an essential role in order to prevent traffic accidents. However, there is no way to prove integrity by evidence corruption, fabrication and etc. For this reason, we propose a method to guarantee the integrity of image through hash value generated by using PingPong 256 encryption algorithm for integrity verification in this paper.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.5
• /
• pp.298-305
• /
• 2014

In this study, a novel Randomly Shifted Certification Authority Authentication protocol was used in ad hoc networks to provide authentication by considering the MAC layer characteristics. The nodes achieve authentication through the use of public key certificates issued by a CA, which assures the certificate's ownership. As a part of providing key management, the active CA node transfers the image of the stored public keys to other idle CA nodes. Finally the current active CA randomly selects the ID of the available idle CA and shifts the CA ownership by transferring it. Revoking is done if any counterfeit or duplicate non CA node ID is found. Authentication and integrity is provided by preventing MAC control packets, and Enhanced Hash Message Authentication Code (EHMAC) can be used. Here EHMAC with various outputs is introduced in all control packets. When a node transmits a packet to a node with EHMAC, verification is conducted and the node replies with the transmitter address and EHMAC in the acknowledgement.

• Journal of Ubiquitous Convergence Technology
• /
• v.2 no.1
• /
• pp.18-26
• /
• 2008

The invariance relation existing in the non-negative matrix factorization (NMF) is used for constructing robust image hashes in this work. The image is first re-scaled to a fixed size. Low-pass filtering is performed on the luminance component of the re-sized image to produce a normalized matrix. Entries in the normalized matrix are pseudo-randomly re-arranged under the control of a secret key to generate a secondary image. Non-negative matrix factorization is then performed on the secondary image. As the relation between most pairs of adjacent entries in the NMF's coefficient matrix is basically invariant to ordinary image processing, a coarse quantization scheme is devised to compress the extracted features contained in the coefficient matrix. The obtained binary elements are used to form the image hash after being scrambled based on another key. Similarity between hashes is measured by the Hamming distance. Experimental results show that the proposed scheme is robust against perceptually acceptable modifications to the image such as Gaussian filtering, moderate noise contamination, JPEG compression, re-scaling, and watermark embedding. Hashes of different images have very low collision probability. Tampering to local image areas can be detected by comparing the Hamming distance with a predetermined threshold, indicating the usefulness of the technique in digital forensics.