Abstract:Current deep learning‐based image manipulation localization methods achieve impressive performance when rich spatial features and information are fully utilized. However, most of them suffer from the irrelevance of semantic awareness when identifying various manipulation categories. This leads to false alarms on recognizing forged regions. In this paper, we propose a Progressively‐Refined Neural Network (PR‐Net), to localize the tampered regions progressively under a coarse‐to‐fine workflow. Specifically, PR‐N… Show more
“…However, the semantic meaning of the modification probability map is quite weak, and it is difficult to generate precise maps directly using simple backbone networks. To this end, we design a multistage progressive network to estimate the probability maps in an "easy-to-hard" learning paradigm, whose recursive computation process [37][38][39][40] also significantly reduces the network parameters for fast inference.…”
Section: Learning Selection Channels Via Proscnetmentioning
Steganalysis is a detection technology against steganography that embeds secret data into digital media carriers. The selection channel, which indicates the embedding details of steganography, is well recognized in boosting the detection performance of image steganalysis. However, nearly all the selection channels are constructed in a hand-crafted manner, even when they are incorporated into end-to-end deep steganalytic networks, for which the embedding rate and steganographic algorithms also need to be predetermined. Such
“…However, the semantic meaning of the modification probability map is quite weak, and it is difficult to generate precise maps directly using simple backbone networks. To this end, we design a multistage progressive network to estimate the probability maps in an "easy-to-hard" learning paradigm, whose recursive computation process [37][38][39][40] also significantly reduces the network parameters for fast inference.…”
Section: Learning Selection Channels Via Proscnetmentioning
Steganalysis is a detection technology against steganography that embeds secret data into digital media carriers. The selection channel, which indicates the embedding details of steganography, is well recognized in boosting the detection performance of image steganalysis. However, nearly all the selection channels are constructed in a hand-crafted manner, even when they are incorporated into end-to-end deep steganalytic networks, for which the embedding rate and steganographic algorithms also need to be predetermined. Such
“…With the large-scale construction and application of new-generation digital infrastructures such as 5G, industrial Internet, big data centers, and cloud computing, more and more important information systems will carry core businesses and massive amounts of data that are closely related to national security and economic development. 1,2 More and more researchers have begun to focus on artificial intelligence (AI) technology applications, [3][4][5][6] network infrastructure optimization, 7,8 and software security analysis 9,10 for critical infrastructure. The development and research results of these works also bring some inspiration for the study of the security of critical infrastructure for us.…”
Section: Introductionmentioning
confidence: 99%
“…(3) What is the unique identifier generation strategy for Mozi in the distributed hash table (DHT) network? (4) What is the difference between the communication methods of Mozi and infected nodes and normal nodes?…”
With the trend of digital transformation of enterprises, the use of Internet of Things (IoT) devices is increasing. IoT devices that are not protected by security measures have gradually become targets of attackers. Attackers use weak passwords and software vulnerabilities in the device to invade the device and control it to become a node of the botnet. The Mozi botnet was discovered in December 2019, and its attention has increased day by day, and its influence once exceeded Mirai. After a preliminary reverse analysis of the Mozi samples, we have continued to track the development and changes of the Mozi botnet since February 2021. First, through the in-depth analysis of the communication principles of the Mozi botnet and the distributed sloppy hash table protocol, we have proposed an in-depth analysis of the Mozi botnet. The active detection method of Mozi, through daily and continuous tracking of the number of Mozi nodes, is infinitely close to the boundary of the Mozi network. On the basis of the collected detection data, we give our conclusions on Mozi's node size, global geographic distribution, 24-hour global activity, equipment composition, and Mozi botnet countermeasures.Through this study, we found that the security of IoT devices around the world is not optimistic, and there is an urgent need to increase the security protection
“…To pay more attention to the relevant areas of the image to improve the performance on removing rain streaks, some attention modules are introduced. [10][11][12][13][14] Though these methods achieved state-of-the-art results, dividing the rain image into a rain part and a background part remains challenging. In the real world, there are rain streaks with different directions and densities, and these methods can only extract information about rain streaks in a single direction, and some rain streaks are very similar to the background, which leads to the loss of important background information while removing rain streaks.…”
Section: Introductionmentioning
confidence: 99%
“…There are also networks that use FPN 9 to remove rain on multi‐scale features. To pay more attention to the relevant areas of the image to improve the performance on removing rain streaks, some attention modules are introduced 10–14 …”
Rain streaks can seriously degrade the visual quality of an image and are detrimental to subsequent algorithms such as object detection and semantic segmentation. Therefore, removing rain streaks is a very important task. The deraining task has two main limitations: the first is to encode information about rain streaks in different densities and directions, the second is to keep the background details of the image while removing the rain streak. To address these limitations, we propose an effective algorithm, called multi-stage and multi-scale joint channel coordinate attention fusion network (MMAFN). We mainly propose a two-stage network structure, both of which use an encoderdecoder network to extract features. The first-stage network extracts coarse features and the second-stage network integrates the features of the former to further refine features. We design the joint channel coordinate attention block to encode features of rain streaks in different directions and densities. In addition, to better fuse features of different scales and enhance the generalization performance of the network, the inception attention branch block and the multi-level feature fusion block are designed. Extensive experiments substantiate the superiority of the proposed network
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.