Image recognition algorithm undecimated wavelet transform coupling moment

The image forgery detection technology based on non sampling wavelet transform coupling with Zernike moments is proposed in this article. Specifically, LL and HH sub-bands are obtained through non sampling wavelet transform to calculate the similarity and the diversity of the image blocks, and then LL similarity and HH diversity are combined for dual judgment. Meanwhile, Zernike moments are introduced therein to construct distance matrix for image feature matching. Finally, the images are selected from CASIA TIDEV1.0 database for algorithm evaluation, and the experimental result shows: the algorithm proposed in the article has the features of good noise immunity, good compression resistance, high algorithm accuracy, low false negative rate and low false positive rate.

Image forgery has become common due to the availability of high-quality image editing softwares. For detecting image forgery there is a need to have important features of the image. For obtaining the image features we need a suitable transform. One of the important and commonly used transform is discrete wavelet transform that can provide spatial and frequency related information of a signal. However, it provides ambiguous information due to its shift variant property. This ambiguity can be overcome using the UWT due to its shift invariance property. In forgery, some operations are applied to an image at different locations. For instance same type of details at different locations, the UWT provides the output of same nature, whereas the DWT doesn't. Due to this property, the features extracted in undecimated wavelet transform (UWT) domain provide better results in many applications like denoising, change detection, etc. In this paper, image features are extracted using the Markov model after transforming it into UWT domain. To evaluate the performance CASIA v1.0, Columbia Color and DSO-1 databases are used. The support vector machine with the linear kernel applied to separate the forged and pristine images. We experimentally obtain better results using the UWT transform as compared to the DWT transform on all these three databases.

A survey on deep learning-based image forgery detection

Password-based authentication system has been praised for its user-friendly, cost-effective, and easily deployable features. It is arguably the most commonly used security mechanism for various resources, services, and applications. On the other hand, it has well-known security flaws, including vulnerability to guessing attacks. Present state-of-the-art approaches have high overheads, as well as difficulties and unreliability during training, resulting in a poor user experience and a high false positive rate. As a result, a lightweight authentication compromise detection model that can make accurate detection with a low false positive rate is required.In this paper we propose – LOG-OFF – a behavior-based authentication compromise detection model. LOG-OFF is a lightweight model that can be deployed efficiently in practice because it does not include a labeled dataset. Based on the assumption that the behavioral pattern of a specific user does not suddenly change, we study the real-world authentication traffic data. The dataset contains more than 4 million records. We use two features to model the user behaviors, i.e., consecutive failures and login time, and develop a novel approach. LOG-OFF learns from the historical user behaviors to construct user profiles and makes probabilistic predictions of future login attempts for authentication compromise detection. LOG-OFF has a low false positive rate and latency, making it suitable for real-world deployment. In addition, it can also evolve with time and make more accurate detection as more data is being collected.

Aims/ objectives: To demontrate effectiveness of Zernike Moments for Image Classification. Zernike moment(ZM) is an excellent region-based moment which has attracted the attentions of many image processing researchers since its first application to image analysis. Many papers have been published on several works done on ZM but no single paper ever give a detailed information of how the computation of ZM is done from the time the image is captured to the computation of ZM. This work showed how to effectively apply ZM on RGB images. We have demonstrated the effectiveness of Zernike moment in image classification system. A neuro-genetic intelligent system has been built with PNN classifier. The feature extracted viz ZM and Geometric features were further subjected to GA to bring the best combinatorial features for optimal accuracy. The algebraic structure of our novel fitness function enabled the GA to select the best results. The 10-fold CV used enabled the whole system to be unbiased giving a classification accuracy of 90.05%. A demonstration of affine properties of ZM are comprehensively stated and explained. In summary, the ZM enabled the classifier to have improved accuracy of 91% as compared with Geometric features with 89% accuracy.

The problem of ensuring the authenticity of visual content is becoming much more pressing in such a rapid proliferation of digital media, when image forgery techniques become ever more sophisticated, more reliable methods for achieving this are required.This paper discusses a holistic approach to detecting image forgery by combining cryptographic methods with a new set of artificial intelligence (AI) methods.Several limitations of traditional detection methods such as error level analysis (ELA), which depends on the invariance of spatially local distributions within individual blocks, are examined concerning the detection of complex manipulations.We rely on cryptographic approaches to achieve high integrity verification by identifying alterations through MD5 hashing of unique hash comparisons.Further, the study employs open-source contributions of advanced image analysis such as texture, color profiling, and shape recognition to discover inconspicuous irregularities in such tampered images with OpenCV.Other AI driven models including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) and Vision Transformers (ViTs) further contribute to the achievement of forgery detection by leveraging multi scale feature learning, temporal analysis and self-attention.The proposed method combines MD5 hashing with these advanced AI techniques to achieve a dual layered approach for enhancing detection accuracy and adaptability to various manipulation methods including deepfake, splice, and copy move type forgeries.The proposed system is demonstrated experimentally, with significant improvements in detection accuracy and robustness over traditional methods shown.Providing a scalable and adaptable framework for preserving the integrity of digital visual content in an environment with an evolving landscape of digital manipulation, this research provides a rich set of insights about cryptographic and AI techniques integration.

This study aims to determine the watermark resistance to different attacks as well as the PSNR level, both of which are essential requirements of watermarking. In our research, we came up with an intelligent design based on NSCT-SVD that fulfills these requirements to a great extent and we managed to use different-sized images for watermark instead of using logos on the host images. Yet we were able to improve PSNR levels and resistance to various attacks. In this paper an NSCT-SVD-based smart watermark model is proposed. We first compare the PSO and PSO-GA algorithms for greater stability using larger SFs obtained by the PSO-GA-AI algorithm. The resulting host image is then decomposed by NSCT transform to obtain images below the low frequency range. Stationary Wavelet Transform (SWT) is performed once on these coefficients and the low frequency coefficients are fed to SVD. Afterwards, SWT transform is performed on the watermark image and the transform is once again taken from the HL coefficients and the LL frequencies are given to the SVD conversion. The rest of image process is insertion. This insertion process dramatically increases the visual transparency and PSNR value. The experiment shows that such a model is able to resist the repeated image attacks with better visibility and power. These results are compared before and after using SWT. We have used a PSO-based algorithm for better results on the False Positive rate in the embedding phase.

A multi-task self-supervised approach for mass detection in automated breast ultrasound using double attention recurrent residual U-Net.

The ever increasing prevalence of smartphones and the popularity of social network platforms have facilitated instant sharing of multimedia content through social networks. However, the ease in taking and sharing photos and videos through social networks also allows privacy-intrusive and illegal content to be widely distributed. As such, images captured and shared by users on their profiles are considered as significant digital evidence for social network data analysis. The Sensor Pattern Noise (SPN) caused by camera sensor imperfections during the manufacturing process mainly consists of the Photo-Response Non-Uniformity (PRNU) noise that can be extracted from taken images without hacking the device. It has been proven to be an effective and robust device fingerprint that can be used for different important digital image forensic tasks, such as image forgery detection, source device identification and device linking. Particularly, by fingerprinting the camera sources captured a set of shared images on social networks, User Profile Linking (UPL) can be performed on social network platforms. The aim of this thesis is to present effective and robust methods and algorithms for better fulfilling shared image analysis based on SPN. We propose clustering and classification based methods to achieve Smartphone Identification (SI) and UPL tasks, given a set of images captured by a known number of smartphones and shared on a set of known user profiles. The important outcome of the proposed methods is UPL across different social networks where the clustered images from one social network are applied to fingerprint the related smartphones and link user profiles on the other social network. Also, we propose two methods for large-scale image clustering of different types of the shared images by users, without prior knowledge about the types and number of the smartphones.

Keypoint-based and block-based methods are two main categories of techniques for detecting copy-move forged images, one of the most common digital image forgery schemes. In general, block-based methods suffer from high computational cost due to the large number of image blocks used and fail to handle geometric transformations. On the contrary, keypoint-based approaches can overcome these two drawbacks yet are found difficult to deal with smooth regions. As a result, fusion of these two approaches is proposed for effective copy-move forgery detection. First, our scheme adaptively determines an appropriate initial size of regions to segment the image into non-overlapped regions. Feature points are extracted as keypoints using the scale invariant feature transform (SIFT) from the image. The ratio between the number of keypoints and the total number of pixels in that region is used to classify the region into smooth or non-smooth (keypoints) regions. Accordingly, block based approach using Zernike moments and keypoint based approach using SIFT along with filtering and post-processing are respectively applied to these two kinds of regions for effective forgery detection. Experimental results show that the proposed fusion scheme outperforms the keypoint-based method in reliability of detection and the block-based method in efficiency.

Digital image forgery detection using passive techniques: A survey

Image forgery detection by transforming local descriptors into deep-derived features

Malware detection engines are required a high True Positive Rate (TPR) and low False Positive rate (FPR). For example, to obtain the VB100 certification conducted by Virus Bulletin in the U.K., the detector's TPR must be 99.5% or higher, and FPR less than 0.01%. However, it is difficult for signature-based malware detection engines to detect zero-day or new variants of malware. For such malware, an approach based on machine learning is considered effective because the features of specimens are analyzed in a complex manner. Therefore, we created a malware detection model from surface analysis logs, and PE header dumps by machine learning using the FFRI Dataset 2018. Furthermore, we verified the accuracy under the constraint that the FPR is less than a certain value. As a result, we succeeded in creating a new model with high accuracy: when FPR is set to be less than 1%, TPR is 99.7%, when FPR is set to be less than 0.1%, TPR is 98.7%, and when FPR is set to be less than 0.01% and TPR is 94.5%. In addition, we revealed features with high contribution to malware detection in this model.

Copy-move forgery is a type of image tampering that involves copying a portion of an image and pasting it to another part of the same image with the intention of deceiving the viewer. In recent years, many approaches have been proposed to detect copy-move forgery, including those based on local binary patterns (LBP). In this paper, we perform a comprehensive evaluation of LBP-based methods for copy-move forgery detection using a dataset of 50 digital images. We compare the performance of four LBP-based methods, namely LBP, SIFT and SURF using metrics such as accuracy, precision, recall, and F1-score. Our results show that LBP outperforms the other methods in terms of accuracy and F1-score, while SIFT has the highest precision and recall. We also investigate the effect of various parameters, such as patch size and threshold values, on the performance of LBP. Our study provides valuable insights into the strengths and weaknesses of LBP-based methods for copy-move forgery detection, which can guide future research in this area. This study evaluates the performance of Local Binary Patterns (LBP) for detecting copy-move forgery in digital images. LBP is a widely used feature extraction technique in image processing and has been applied to various computer vision tasks, including forgery detection. The comparative study involves analyzing the accuracy, precision, recall, and F1-score of LBP and other popular forgery detection techniques, including SIFT and SURF, using a dataset of 50 digital images. The results show that LBP performs better than the other techniques, achieving an accuracy of 96.6%, precision of 94.0%, recall of 100%, and F1-score of 96.9%. This study provides useful insights for researchers and practitioners in the field of forgery detection, particularly for those interested in using LBP as a feature extraction technique.

Nowadays most of the multimedia contents are in digital form. With the increased use of powerful computer and image processing software, along with wide availability of digital cameras have given rise to huge numbers of doctored images. Several forgery detection algorithms are available. However, these techniques do not address the issue from cryptographic point of view. As a result, even if an image or video is identified as doctored, most of the time it is not possible to track the actual offender. Here, we present a perceptual hash function which can be used for both detection of forged images as well as tracking of forgers.