Multimodal malicious web page detection technology based on content and image fusion

Cybercrime has been on the rise in recent years. Cybercriminals target Internet users and commit illegal acts. Malicious web pages are an easy tool to obtain sensitive personal information from Internet users, install malware on their computers, and expose them to cyberspace. More advanced techniques are used by the attackers to inject the malicious code into the normal legitimate webpages or create a web page with illegal content and then spread the URL through various possible media to perform the intended action. Internet users who click the link will be in their nest. Identifying such URLs or web pages can be a daunting task for internet users. So, the researchers using different machine/deep learning methods with different set features that are derived from URL, content, and server-based information of the web page to detect or classify the malicious web pages. Most attacks, including drive-by downloads, phishing, and injections, conceals the maliciously intended code or link in the content of legitimate or purportedly legitimate webpage. Many current research work uses the URL based features due to its risk-free processing. Only less attention is given to the content-based features. That hides the vital area of features to better classification. To address this issue, this paper focus on web content-based features for malicious web page classification. The result shows, the proposed method performs better in terms of accuracy.

This paper proposes a multimodal fusion 3D target detection algorithm based on the attention mechanism to improve the performance of 3D target detection. The algorithm utilizes point cloud data and information from the camera. For image feature extraction, the ResNet50 + FPN architecture extracts features at four levels. Point cloud feature extraction employs the voxel method and FCN to extract point and voxel features. The fusion of image and point cloud features is achieved through regional point fusion and voxel fusion methods. After information fusion, the Coordinate and SimAM attention mechanisms extract fusion features at a deep level. The algorithm's performance is evaluated using the DAIR-V2X dataset. The results show that compared to the Part-A2 algorithm; the proposed algorithm improves the mAP value by 7.9% in the BEV view and 7.8% in the 3D view at IOU = 0.5 (cars) and IOU = 0.25 (pedestrians and cyclists). At IOU = 0.7 (cars) and IOU = 0.5 (pedestrians and cyclists), the mAP value of the SECOND algorithm is improved by 5.4% in the BEV view and 4.3% in the 3D view, compared to other comparison algorithms.

Development of an online prediction system for soil organic matter and soil moisture content based on multi-modal fusion

Client-side attacks have become an increasing problem on the Internet today. Malicious web pages launch so-called drive-by-download attacks that are capable to gain complete control of a user’s machine by merely having that user visit a malicious web page. Criminals that are behind the majority of these malicious web pages are highly sensitive to location, language and economic trends to increase their return on investment. In this paper, a comprehensive measurement study of malicious web servers on the .nz domain is presented. The risk of drive-by-download attacks has been compared with other domains showing no elevated risk for the .nz domain. However, a comprehensive assessment of the .nz domain showed the existence of malicious web pages across a variety of types of web pages. Blacklisting services showed limited success to protect against such malicious web pages. This is primarily attributed to the highly dynamic nature of malicious web pages. Over a period of eight months, the .nz domain was monitored and continuous shifting of malicious behavior of web pages has been observed. The rates observed show that on average 50% of malicious URLs identified change monthly. The rates pose a challenge to blacklisting services as well as a risk to end users with rapid dissemination of zero-day attacks. Frequent scans of the web are required to obtain a good up-to-date view of the threat landscape.KeywordsMeasurement StudyMalicious BehaviorProxy CacheMalicious ContentDistribute System Security SymposiumThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

The image feature fusion is a kind of data fusion that is based on spectral structure and texture feature of the objects. This paper proposed feature fusion after enhancing image edge with wavelet's multi-resolution analysis to largely improve image's definition and resolving power. In the fusion process, instead of using the conventional HIS-Wavelet fusion, we directly introduced RGB-Wavelet transformation which decomposed RGB bands of the multi-spectral image and high-resolution image by wavelet separately, then used low frequent parts of the R,G,B bands and high frequent parts of the high-resolution image to do the image fusion, finally had new R,G,B bands as the new fusion image. In the way, it not only improved definition and resolution of the multi-spectral image, but also retained the color feature of multi-spectral image which is important for multi-spectral fusion. At last we validated the conclusion with an experiment. This method was based on wavelet multi-resolution analysis and RGB color space, so it didn't generate any computing error of color space transform. Compared the fusion results of RGB-wavelet and HIS-wavelet methods, it could find that not only precision of visual estimation but also guide lines of quantitative analysis such as definition, space resolution had greater improvement.

Extraction of soybean planting area based on feature fusion technology of multi-source low altitude unmanned aerial vehicle images

In this study, we used eight millet varieties and took visible-near-infrared hyperspectral images of 480 millet samples. Spectral and image characteristics, including texture and color features, of the millet samples were extracted from the hyperspectral images. Support vector machine (SVM) models for millet variety identification were established using the extracted spectral and image characteristics. An attention-convolutional recurrent neural network (attention- CRNN) model with attention mechanism was introduced for the identification of millet varieties, and the SVM and attention- CRNN models for millet variety identification were established using an image and spectral features fusion method. We found that the highest mathematical transformation method was the reciprocal logarithmic method. The identification accuracy of the SVM cultivar classification model with the reciprocal logarithmic spectral characteristics curve was 73.13%. The overall identification accuracy of the SVM model for the eight millet varieties using the image features was only 61.25%. The identification accuracy of the SVM model using the image and spectral information fusion method greatly improved the overall accuracy rate to 77.5%, and the minimum discrimination accuracy of the millet varieties increased from 50 to 65%. The overall identification accuracy of the attention-CRNN model was 87.50%, which is 10% higher than that of the SVM model, and the minimum discrimination accuracy of the millet varieties increased from 65 to 90%. The results show that the attention-CRNN model improved the overall identification accuracy of the eight millet varieties and greatly improved the minimum identification accuracy. The attention-CRNN model shows great potential for the nondestructive identification of millet and possibly other small grain varieties.

Detecting malicious web pages used in attacks and building blacklists and signatures from them are done to protect users against drive-by download attacks. Gathering the content on web pages by crawling and evaluating it to check if it is malicious can help in detecting malicious web pages. Methods that apply supervised machine learning to this evaluation are proposed for detecting malicious web pages from a massive amount of web pages. However, these methods need manual inspections for preparing training data when classifiers are retrained in accordance with changes in the content on malicious web pages. In this paper, we propose a method that evaluates whether web pages are malicious and needs only the discrimination results of web pages identified by high-interaction honeyclients to prepare training data. This method evaluates maliciousness on the basis of the structural similarity of redirection chains arising from drive-by download attacks. The results of our experiments with two years of data showed that the accuracy of our method was about 20\% higher than that of the previous method.

Multi-modality image fusion applied to improve image quality has drawn great attention from researchers in recent years. However, noise is actually generated in images captured by different types of imaging sensors, which can seriously affect the performance of multi-modality image fusion. As the fundamental method of noisy image fusion, source images are denoised first, and then the denoised images are fused. However, image denoising can decrease the sharpness of source images to affect the fusion performance. Additionally, denoising and fusion are processed in separate processing modes, which causes an increase in computation cost. To fuse noisy multi-modality image pairs accurately and efficiently, a multi-modality image simultaneous fusion and denoising method is proposed. In the proposed method, noisy source images are decomposed into cartoon and texture components. Cartoon-texture decomposition not only decomposes source images into detail and structure components for different image fusion schemes, but also isolates image noise from texture components. A Gaussian scale mixture (GSM) based sparse representation model is presented for the denoising and fusion of texture components. A spatial domain fusion rule is applied to cartoon components. The comparative experimental results confirm the proposed simultaneous image denoising and fusion method is superior to the state-of-the-art methods in terms of visual and quantitative evaluations.

As the global population ages, the socioeconomic burden caused by Alzheimer's disease (AD) is rising. Existing clinical interventions mostly focus on delaying the course of the disease and lack support for the accuracy and timeliness of early diagnosis, which has become a key bottleneck restricting the prevention and treatment of AD. This study aims to explore the application value of multi-modal medical image fusion technology in the early diagnosis of AD under the guidance of artificial intelligence (AI), and to verify its advantages and feasibility compared with single-modal imaging diagnosis. The research will integrate multi-modal imaging data such as structural magnetic resonance imaging (sMRI), positron emission tomography (PET) and diffusion tensor imaging (DTI), and complete the extraction, matching and fusion of image features through AI models such as convolutional neural networks (CNN) or Transformer to build an early diagnosis model for AD; and use clinically confirmed AD high-risk groups (patients with mild cognitive impairment) and healthy controls as the research subjects If this study proves feasible, it can provide efficient and accurate technical support for early AD screening, thereby providing a new practical path for delaying the course of the disease and reducing social costs.

Drive-by-download attacks are client-side attacks that originate from web servers that are visited by web browsers. While many web browsers are vulnerable to the drive-by-download attacks, the cost of detecting malicious web pages that launch drive-by-download attacks is expensive. High-interaction client honeypots are security devices capable of detecting malicious web pages; however, their slow and expensive operations in web page visiting have been considered as a problem. The high-interaction client honeypots employ a visitation algorithm to pinpoint which page has made an unauthorized change of system state when any unauthorized change of the system state occurred after visiting suspicious web pages. To improve the performance of the high-interaction client honeypots, we propose a new visitation algorithm, logarithmic divide-and-conquer (LDAC), for identifying malicious web pages. The LDAC algorithm is an enhanced version of the existing binary divide-and-conquer (BDAC) algorithm. If any system state is abnormally changed after having visited k suspicious web pages concurrently, our LDAC algorithm divides the buffer of k pages into [log2k] pieces and recursively visits the pieces until the malicious page or pages are identified, while the BDAC splits the buffer into k/2 portions. Experimental results show that the LDAC has improved performance of the system up to 15 percent compared to the BDAC algorithm.

Web browsers are often used as a popular means for compromising Internet hosts. An attacker may inject a JavaScript malware into a web page. When a victim visits this page, the malware is executed and attempts to exploit a specific browser vulnerability or download an unwanted program. Obfuscated JavaScript malware can easily evade signature-based detection by changing the appearance of JavaScript code. To address this problem, some previous studies have used static analysis in which some features are extracted from both benign and malicious web pages, and then a classifier is trained to distinguish between them. Because nowadays benign JavaScript code is often obfuscated, static analysis techniques generate many false alarms. In this paper, we use dynamic analysis to monitor a web page for detecting obfuscated JavaScript malware. We first load a set of malicious web pages in a real web browser and collect a sequence of predictive function calls using internal function debugging for each of them. We then group similar sequences into the same cluster based on the normalized Levenshtein distance (NLD) metric and generate a so-called behavioral signature for each cluster. A web page is detected as malicious only if the sequence of its intercepted function calls is matched with at least one generated behavioral signature. Our evaluation results show that the generated behavioral signatures are able to detect obfuscated JavaScript malware with a low false alarm rate.

The appearance of pedestrians can vary greatly from image to image, and different pedestrians may look similar in a given image. Such similarities and variabilities in the appearance and clothing of individuals make the task of pedestrian re-identification very challenging. Here, a pedestrian re-identification method based on the fusion of local features and gait energy image (GEI) features is proposed. In this method, the human body is divided into four regions according to joint points. The color and texture of each region of the human body are extracted as local features, and GEI features of the pedestrian gait are also obtained. These features are then fused with the local and GEI features of the person. Independent distance measure learning using the cross-view quadratic discriminant analysis (XQDA) method is used to obtain the similarity of the metric function of the image pairs, and the final similarity is acquired by weight matching. Evaluation of experimental results by cumulative matching characteristic (CMC) curves reveals that, after fusion of local and GEI features, the pedestrian reidentification effect is improved compared with existing methods and is notably better than the recognition rate of pedestrian re-identification with a single feature.

The aim of this study was to assess the changes in the characteristics of rheumatoid arthritis information on the Internet over a 15-year period and the positioning of Web sites posted by universities, hospitals, and medical associations. We replicated the methods of a 2001 study assessing rheumatoid arthritis information on the Internet using WebCrawler. All Web sites and pages were critically assessed for relevance, scope, authorship, type of publication, and financial objectives. Differences between studies were considered significant if 95% confidence intervals did not overlap. Additionally, we added a Google search with assessments of the quality of content of web pages and of the Web sites posted by medical institutions. There were significant differences between the present study's WebCrawler search and the 2001-referent study. There were increases in information sites (82 vs 36%) and rheumatoid arthritis-specific discussion pages (59 vs 8%), and decreases in advertisements (2 vs 48%) and alternative therapies (27 vs 45%). The quality of content of web pages is still dispersed; just 37% were rated as good. Among the first 300 hits, 30 (10%) were posted by medical institutions, 17 of them in the USA. Regarding readability, 7% of these 30 web pages required 6years, 27% required 7-9years, 27% required 10-12years, and 40% required 12 or more years of schooling. The Internet has evolved in the last 15years. Medical institutions are also better positioned. However, there are still areas for improvement, such as the quality of the content, leadership of medical institutions, and readability of information.

In this paper, we propose a novel method to realize multimodal image registration and fusion in a mutually reinforcing framework, termed as RFNet. We handle the registration in a coarse-to-fine fashion. For the first time, we exploit the feedback of image fusion to promote the registration accuracy rather than treating them as two separate issues. The fine-registered results also improve the fusion performance. Specifically, for image registration, we solve the bottlenecks of defining registration metrics applicable for multi-modal images and facilitating the network convergence. The metrics are defined based on image translation and image fusion respectively in the coarse and fine stages. The convergence is facilitated by the designed metrics and a deformable convolution-based network. For image fusion, we focus on texture preservation, which not only increases the information amount and quality of fusion results but also improves the feedback of fusion results. The proposed method is evaluated on multi-modal images with large global parallaxes, images with local misalignments and aligned images to validate the performances of registration and fusion. The results in these cases demonstrate the effectiveness of our method.