Explore the vast range of titles available.

With the explosive growth of false information on social media platforms, the automatic detection of multimodal false information has received increasing attention. Recent research has significantly contributed to multimodal information exchange and fusion, with many methods attempting to integrate unimodal features to generate multimodal news representations. However, they still need to fully explore the hierarchical and complex semantic correlations between different modal contents, severely limiting their performance detecting multimodal false information. This work proposes a two-stage detection framework for multimodal false information detection, called ASMFD, which is based on image aesthetic similarity to segment and explores the consistency and inconsistency features of images and texts. Specifically, we first use the Contrastive Language-Image Pre-training (CLIP) model to learn the relationship between text and images through label awareness and train an image aesthetic attribute scorer using an aesthetic attribute dataset. Then, we calculate the aesthetic similarity between the image and related images and use this similarity as a threshold to divide the multimodal correlation matrix into consistency and inconsistency matrices. Finally, the fusion module is designed to identify essential features for detecting multimodal false information. In extensive experiments on four datasets, the performance of the ASMFD is superior to state-of-the-art baseline methods.

The spread of misinformation during the COVID-19 pandemic raised widespread concerns about public health communication and media reliability. In this study, we focus on these issues as they manifested in Romanian-language media and employ Large Language Models (LLMs) to classify misinformation, with a particular focus on super-narratives—broad thematic categories that capture recurring patterns and ideological framings commonly found in pandemic-related fake news, such as anti-vaccination discourse, conspiracy theories, or geopolitical blame. While some of the categories reflect global trends, others are shaped by the Romanian cultural and political context. We introduce a novel dataset of fake news centered on COVID-19 misinformation in the Romanian geopolitical context, comprising both annotated and unannotated articles. We experimented with multiple LLMs using zero-shot, few-shot, supervised, and semi-supervised learning strategies, achieving the best results with an LLaMA 3.1 8B model and semi-supervised learning, which yielded an F1-score of 78.81%. Experimental evaluations compared this approach to traditional Machine Learning classifiers augmented with morphosyntactic features. Results show that semi-supervised learning substantially improved classification results in both binary and multi-class settings. Our findings highlight the effectiveness of semi-supervised adaptation in low-resource, domain-specific contexts, as well as the necessity of enabling real-time misinformation tracking and enhancing transparency through claim-level explainability and fact-based counterarguments.

Vehicular networks utilize wireless communication among vehicles and between vehicles and infrastructures. While vehicular networks offer a wide range of benefits, the security of these networks is critical for ensuring public safety. The transmission of false information by malicious nodes (vehicles) for selfish gain is a security issue in vehicular networks. Mitigating false information is essential to reduce the potential risks posed to public safety. Existing methods for false information detection in vehicular networks utilize various approaches, including machine learning, blockchain, trust scores, and statistical techniques. These methods often rely on past information about vehicles, historical data for training machine learning models, or coordination between vehicles without considering the trustworthiness of the vehicles. To address these limitations, we propose a technique for False Information Mitigation using Pattern-based Anomaly Detection (FIM-PAD). The novelty of FIM-PAD lies in using an unsupervised learning approach to learn the usual patterns between the direction of travel and speed of vehicles, considering the variations in vehicles’ speeds in different directions. FIM-PAD uses only real-time network characteristics to detect the malicious vehicles that do not conform to the identified usual patterns. The objective of FIM-PAD is to accurately detect false information in vehicular networks with minimal processing delays. Our performance evaluations in networks with high proportions of malicious nodes confirm that FIM-PAD on average offers a 38% lower data processing delay and at least 19% lower false positive rate compared to three other existing techniques.

The popularity and development of social media have made it more and more convenient to spread rumors, and it has become especially important to detect rumors in massive amounts of information. Most of the traditional rumor detection methods use the rumor content or propagation structure to mine rumor characteristics, ignoring the fusion characteristics of the content and structure and their interaction. Therefore, a novel rumor detection method based on heterogeneous convolutional networks is proposed. First, this paper constructs a heterogeneous map that combines both the rumor content and propagation structure to explore their interaction during rumor propagation and obtain a rumor representation. On this basis, this paper uses a deep residual graph convolutional neural network to construct the content and structure interaction information of the current network propagation model. Finally, this paper uses the Twitter15 and Twitter16 datasets to verify the proposed method. Experimental results show that the proposed method has higher detection accuracy compared to the traditional rumor detection method.

In the existing false information detection methods, the quality of the extracted single-modality features is low, the information between different modalities cannot be fully fused, and the original information will be lost when the information of different modalities is fused. This paper proposes a false information detection via multimodal feature fusion and multi-classifier hybrid prediction. In this method, first, bidirectional encoder representations for transformers are used to extract the text features, and S win-transformer is used to extract the picture features, and then, the trained deep autoencoder is used as an early fusion method of multimodal features to fuse text features and visual features, and the low-dimensional features are taken as the joint features of the multimodalities. The original features of each modality are concatenated into the joint features to reduce the loss of original information. Finally, the text features, image features and joint features are processed by three classifiers to obtain three probability distributions, and the three probability distributions are added proportionally to obtain the final prediction result. Compared with the attention-based multimodal factorized bilinear pooling, the model achieves 4.3% and 1.2% improvement in accuracy on Weibo dataset and Twitter dataset. The experimental results show that the proposed model can effectively integrate multimodal information and improve the accuracy of false information detection.

Intrusion detection system (IDS) has been developed to protect the resources in the network from different types of threats. Existing IDS methods can be classified as either anomaly based or misuse (signature) based or sometimes combination of both. This paper proposes a novel misuse based intrusion detection system to detect five categories such as: Exploit, DOS, Probe, Generic and Normal in a network. Further, most of the related works on IDS are based on KDD99 or NSL-KDD 99 data set. These data sets are considered obsolete to detect recent types of attacks and have no significance. In this paper UNSW-NB15 data set is considered as the offline dataset to design own integrated classification based model for detecting malicious activities in the network. Performance of the proposed integrated classification based model is considerably high compared to other existing decision tree based models to detect these five categories. Moreover, this paper generates its own real time data set at NIT Patna CSE lab (RTNITP18) which acts as the working example of proposed intrusion detection model. This RTNITP18 dataset is considered as a test data set to evaluate the performance of the proposed intrusion detection model. The performance analysis of the proposed model with UNSW-NB15 (benchmark data set) and real time data set (RTNITP18) shows higher accuracy, attack detection rate, mean F-measure, average accuracy, attack accuracy, and false alarm rate in comparison to other existing approaches. Proposed IDS model acts as the dog watcher to detect different types of threat in the network.

Crowdfunding platforms offer founders the possibility to collect funding for project realization. With the advent of these platforms, the risk of fraud has risen. Fraudulent founders provide inaccurate information or pretend interest toward a project. Within this study, we propose deception detection support mechanisms to address this novel type of Internet fraud. We analyze a sample of fraudulent and nonfraudulent projects published at a leading crowdfunding platform. We examine whether the analysis of dynamic communication during the funding period is valuable for identifying fraudulent behavior-apart from analyzing only the static information related to the project. We investigate whether content-based cues and linguistic cues are valuable for fraud detection. The selection of cues and the subsequent feature engineering is based on theories in areas of communication, psychology, and computational linguistics. Our results should be helpful to the stakeholders of crowdfunding platforms and researchers of fraud detection.

Synthetic aperture radar (SAR) ship detection has been playing an increasingly essential role in marine monitoring in recent years. The lack of detailed information about ships in wide swath SAR imagery poses difficulty for traditional methods in exploring effective features for ship discrimination. Being capable of feature representation, deep neural networks have achieved dramatic progress in object detection recently. However, most of them suffer from the missing detection of small-sized targets, which means that few of them are able to be employed directly in SAR ship detection tasks. This paper discloses an elaborately designed deep hierarchical network, namely a contextual region-based convolutional neural network with multilayer fusion, for SAR ship detection, which is composed of a region proposal network (RPN) with high network resolution and an object detection network with contextual features. Instead of using low-resolution feature maps from a single layer for proposal generation in a RPN, the proposed method employs an intermediate layer combined with a downscaled shallow layer and an up-sampled deep layer to produce region proposals. In the object detection network, the region proposals are projected onto multiple layers with region of interest (ROI) pooling to extract the corresponding ROI features and contextual features around the ROI. After normalization and rescaling, they are subsequently concatenated into an integrated feature vector for final outputs. The proposed framework fuses the deep semantic and shallow high-resolution features, improving the detection performance for small-sized ships. The additional contextual features provide complementary information for classification and help to rule out false alarms. Experiments based on the Sentinel-1 dataset, which contains twenty-seven SAR images with 7986 labeled ships, verify that the proposed method achieves an excellent performance in SAR ship detection.

The Internet of Things (IoT) interconnects billions of sensors and actuators to serve a meaningful purpose. However, it is always vulnerable to various menaces. Thus, IoT security represents a big concern in the research field. Various tools were developed to mitigate these security issues. So, Intrusion detection systems (IDS) have gained much attention in the research community due to their critical role in maintaining network security. In this work, we integrate a network IDS (NIDS) to enhance IoT security. This paper presents a network intrusion detection model for IoT environments using a K-Nearest Neighbors (K-NN) classifier and feature selection. We built the NIDS using the K-NN algorithm to improve the IDS accuracy (ACC) and detection rate (DR). Furthermore, the principal component analysis (PCA), univariate statistical test, and genetic algorithm (GA) are used for feature selection separately to improve the data quality and select the ten best performing features. The performance evaluation of our model is performed on the Bot-IoT dataset. After applying the feature selection, the models have shown promising results regarding ACC, DR, false alarm rate (FAR), and predicting time. Our proposed model provided 99.99% ACC and maintained its superior performance for the ten selected features. Furthermore, we calculated the prediction time, as we consider it critical in building IDS for IoT, and by applying feature selection, we reduced it significantly from 51,182.22 s to under a minute. This novel model presents many advantages and reliable performances compared with previous models relying on the same dataset.

The Internet of Things (IoT) has been rapidly evolving towards making a greater impact on everyday life to large industrial systems. Unfortunately, this has attracted the attention of cybercriminals who made IoT a target of malicious activities, opening the door to a possible attack to the end nodes. Due to the large number and diverse types of IoT devices, it is a challenging task to protect the IoT infrastructure using a traditional intrusion detection system. To protect IoT devices, a novel ensemble Hybrid Intrusion Detection System (HIDS) is proposed by combining a C5 classifier and One Class Support Vector Machine classifier. HIDS combines the advantages of Signature Intrusion Detection System (SIDS) and Anomaly-based Intrusion Detection System (AIDS). The aim of this framework is to detect both the well-known intrusions and zero-day attacks with high detection accuracy and low false-alarm rates. The proposed HIDS is evaluated using the Bot-IoT dataset, which includes legitimate IoT network traffic and several types of attacks. Experiments show that the proposed hybrid IDS provide higher detection rate and lower false positive rate compared to the SIDS and AIDS techniques.