Search Results (98)

According to the literature, the advancement of information and communication technology (ICT) has increased individual exposure to scams, turning fraud victimization into a significant concern. While prior research has primarily focused on socio-demographic predictors of fraud victimization, this study adopts a behavioral perspective that is grounded in the Signal Detection Theory (SDT) to investigate the likelihood determinants of individuals becoming fraud victims. Using survey data of 671 Indonesian respondents analyzed with the Partial Least Squares Structural Equation Modeling (PLS-SEM), we explored the roles of vigilance and financial literacy in moderating the relationship between fraud exposure and victimization. Our findings substantiate the notion that higher exposure to fraudulent activity significantly increases the likelihood of victimization. The results also show that vigilance negatively moderates the relationship between fraud exposure and fraud victimization, suggesting that individuals with higher vigilance are better at identifying scams, thereby decreasing their likelihood of becoming fraud victims. Furthermore, financial literacy is positively related to vigilance, indicating that financially literate individuals are more aware of potential scams. However, the predictive power of financial literacy on vigilance is relatively low. Hence, while literacy helps a person sharpen their indicators for detecting fraud, psychological, behavioral, and contextual factors may also affect their vigilance and decision-making. Full article

Dating applications (DAs) are widely used to establish social and sexual connections among men who have sex with men (MSM), particularly in urban areas. In this study, we aimed to examine the associations between DA use and mental health among Thai MSM. An online cross-sectional survey was completed by 442 MSM residing in Bangkok and urban municipalities across all regions of Thailand. Psychological distress (PD) and probable depression were assessed using the General Health Questionnaire (GHQ-12) and the Patient Health Questionnaire (PHQ-9), respectively. Of the participants, 62.7% were current users, with 33.2% experiencing PD and 33.9% having depression. A logistic regression analysis showed that PD was significantly associated with late-night use (AOR = 2.02, 95% CI: 1.08–3.78), matching failure (AOR = 1.95, 95% CI: 1.12–3.38), rejection (AOR = 2.07, 95% CI: 1.18–3.62), and ghosting (AOR = 1.78, 95% CI: 1.02–3.11). Simultaneously, depression was significantly associated with using DAs with the motivation of hooking up (AOR = 2.27, 95% CI: 1.05–4.93), privacy violations (AOR = 2.76, 95% CI: 1.42–5.38), unsolicited sexual images (AOR = 2.04, 95% CI: 1.11–3.74), physical assault (AOR = 2.97, 95% CI: 1.57–5.61), harassment (AOR = 2.54, 95% CI: 1.37–4.70), scams (AOR = 2.59, 95% CI: 1.41–4.77), and extreme disappointment from DA use (AOR = 5.98, 95% CI: 1.84–19.41). These findings highlight how DA usage patterns and negative experiences may contribute to the poorer mental health among MSM in urban areas. Full article

In today’s business environment, emails are essential across all sectors, including finance and academia. There are two main types of emails: ham (legitimate) and spam (unsolicited). Spam wastes consumers’ time and resources and poses risks to sensitive data, with volumes doubling daily. Current spam identification methods, such as Blocklist approaches and content-based techniques, have limitations, highlighting the need for more effective solutions. These constraints call for detailed and more accurate approaches, such as machine learning (ML) and deep learning (DL), for realistic detection of new scams. Emphasis has since been placed on the possibility that ML and DL technologies are present in detecting email spam. In this work, we have succeeded in developing a hybrid deep learning model, where Long Short-Term Memory (LSTM) and the Gated Recurrent Unit (GRU) are applied distinctly to identify spam email. Despite the fact that the other models have been applied independently (CNNs, LSTM, GRU, or ensemble machine learning classifier) in previous studies, the given research has provided a contribution to the existing body of literature since it has managed to combine the advantage of LSTM in capturing the long-term dependency and the effectiveness of GRU in terms of computational efficiency. In this hybridization, we have addressed key issues such as the vanishing gradient problem and outrageous resource consumption that are usually encountered in applying standalone deep learning. Moreover, our proposed model is superior regarding the detection accuracy (90%) and AUC (98.99%). Though Transformer-based models are significantly lighter and can be used in real-time applications, they require extensive computation resources. The proposed work presents a substantive and scalable foundation to spam detection that is technically and practically dissimilar to the familiar approaches due to the powerful preprocessing steps, including particular stop-word removal, TF-IDF vectorization, and model testing on large, real-world size dataset (Enron-Spam). Additionally, delays in the feature comparison technique within the model minimize false positives and false negatives. Full article

Internet scams have become more sophisticated and prevalent in countries such as Canada, the US, the UK, and Australia. Australia has made some progress in effective scam intervention strategies and seen possible growth in public awareness. However, there is a lack of insight into factors associated with profound shame and embarrassment, emotional distress such as anxiety and depression, and trauma and suicide in scam victims. To fill this gap, this perspective paper aimed to provide insight into the factors associated with the negative mental health impacts of internet scams by integrating a narrative literature review with a victim case study detailing a group’s experience of an investment scam in Australia. It found that internet scams cause emotional and social issues like depression, anxiety, trauma, and isolation, mostly prolonged upon substantial loss. The author’s insight into the intensely negative mental health impacts of an investment scam allows for the presentation of a group who struggled to access adequate support and mental health care in their response to insidious organized crime. Better education, resilience-building, and support systems are needed. These shortcomings call for strategies for tailored digital mental health services such as emotionally attuned, trauma-informed digital companionship through human-like artificial intelligence (AI) applications. Full article

Semantic segmentation plays a critical role in understanding complex urban environments, particularly for autonomous driving applications. However, existing approaches face significant challenges under low-light and adverse weather conditions. To address these limitations, we propose CSANet (Context Spatial Awareness Network), a novel framework that effectively integrates RGB and thermal infrared (TIR) modalities. CSANet employs an efficient encoder to extract complementary local and global features, while a hierarchical fusion strategy is adopted to selectively integrate visual and semantic information. Notably, the Channel–Spatial Cross-Fusion Module (CSCFM) enhances local details by fusing multi-modal features, and the Multi-Head Fusion Module (MHFM) captures global dependencies and calibrates multi-modal information. Furthermore, the Spatial Coordinate Attention Mechanism (SCAM) improves object localization accuracy in complex urban scenes. Evaluations on benchmark datasets (MFNet and PST900) demonstrate that CSANet achieves state-of-the-art performance, significantly advancing RGB-T semantic segmentation. Full article

Deepfake images, synthetic images created using digital software, continue to present a serious threat to online platforms. This is especially relevant for biometric verification systems, as deepfakes that attempt to bypass such measures increase the risk of impersonation, identity theft and scams. Although research on deepfake image detection has provided many high-performing classifiers, many of these commonly used detection models lack generalizability across different methods of deepfake generation. For companies and governments fighting identify fraud, a lack of generalization is challenging, as malicious actors may use a variety of deepfake image-generation methods available through online wrappers. This work explores if combining multiple classifiers into an ensemble model can improve generalization without losing performance across different generation methods. It also considers current methods of deepfake image generation, with a focus on publicly available and easily accessible methods. We compare our framework against its underlying models to show how companies can better respond to emerging deepfake generation methods. Full article

Currently, the phenomenon of deepfakes is becoming increasingly significant, as they enable the creation of extremely realistic images capable of deceiving anyone thanks to deep learning tools based on generative adversarial networks (GANs). These images are used as profile pictures on social media with the intent to sow discord and perpetrate scams on a global scale. In this study, we demonstrate that these images can be identified through various imperfections present in the synthesized eyes, such as the irregular shape of the pupil and the difference between the corneal reflections of the two eyes. These defects result from the absence of physical and physiological constraints in most GAN models. We develop a two-level architecture capable of detecting these fake images. This approach begins with an automatic segmentation method for the pupils to verify their shape, as real image pupils naturally have a regular shape, typically round. Next, for all images where the pupils are not regular, the entire image is analyzed to verify the reflections. This step involves passing the facial image through an architecture that extracts and compares the specular reflections of the corneas of the two eyes, assuming that the eyes of real people observing a light source should reflect the same thing. Our experiments with a large dataset of real images from the Flickr-FacesHQ and CelebA datasets, as well as fake images from StyleGAN2 and ProGAN, show the effectiveness of our method. Our experimental results on the Flickr-Faces-HQ (FFHQ) dataset and images generated by StyleGAN2 demonstrated that our algorithm achieved a remarkable detection accuracy of 0.968 and a sensitivity of 0.911. Additionally, the method had a specificity of 0.907 and a precision of 0.90 for this same dataset. And our experimental results on the CelebA dataset and images generated by ProGAN also demonstrated that our algorithm achieved a detection accuracy of 0.870 and a sensitivity of 0.901. Moreover, the method had a specificity of 0.807 and a precision of 0.88 for this same dataset. Our approach maintains good stability of physiological properties during deep learning, making it as robust as some single-class deepfake detection methods. The results of the tests on the selected datasets demonstrate higher accuracy compared to other methods. Full article

Bank loan prediction (BLP) analyzes the financial records of individuals to conclude possible loan status. Financial records always contain confidential information. Hence, privacy is significant in the BLP system. This research aims to generate a privacy-preserving automated BLP scheme. To achieve this, differential privacy (DP) is combined with machine learning (ML). Using a benchmark dataset, the proposed method analyzes two different DP techniques, namely Laplacian and Gaussian, with five different ML models: Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Logistic Regression (LR), and Categorical Boosting (CatBoost). Each of the DP techniques is evaluated by varying distinct privacy parameters with 10-fold cross-validation, and from the outcome analysis, optimal parameters are nominated to balance privacy and security. The analysis indicates that applying the Laplacian mechanism with a DP budget of 2 and the RF model achieves the highest accuracy of 62.31%. For the Gaussian method, the best accuracy of 81.25% is attained by the CatBoost model in privacy budget 1.5. Additionally, the proposed method uses explainable artificial intelligence (XAI) to show the conclusion capability of DP-integrated ML models. The proposed research shows an efficient method for automated BLP while preserving the privacy of personal financial information and, thus, mitigating vulnerability to scams and fraud. Full article

Object detection in remote sensing images has gained prominence alongside advancements in sensor technology and earth observation systems. Although current detection frameworks demonstrate remarkable achievements in natural imagery analysis, their performance degrades when applied to remote imaging scenarios due to two inherent limitations: (1) complex background interference, which causes object features to be easily obscured by noise, leading to reduced detection accuracy; (2) the variation in object scales leads to a decrease in the model’s generalization ability. To address these issues, we propose a progressive semantic-aware fusion network (ProSAF-Net). First, we design a shallow detail aggregation module (SDAM), which adaptively integrates features across different channels and scales in the early Neck stage through dynamically adjusted fusion weights, fully exploiting shallow detail information to refine object edge and texture representation. Second, to effectively integrate shallow detail information and high-level semantic abstractions, we propose a deep semantic fusion module (DSFM), which employs a progressive feature fusion mechanism to incrementally integrate deep semantic information, strengthening the global representation of objects while effectively complementing the rich shallow details extracted by SDAM, enhancing the model’s capability in distinguishing objects and refining spatial localization. Furthermore, we develop a spatial context-aware module (SCAM) to fully exploit both global and local contextual information, effectively distinguishing foreground from background and suppressing interference, thus improving detection robustness. Finally, we propose auxiliary dynamic loss (ADL), which adaptively adjusts loss weights based on object scales and utilizes supplementary anchor priors to expedite parameter convergence during coordinate regression, thereby improving the model’s positioning accuracy for targets. Extensive experiments on the RSOD, DIOR, and NWPU VHR-10 datasets demonstrate that our method outperforms other state-of-the-art methods. Full article

As cryptocurrency transactions continue to grow, detecting scams within transaction records remains a critical challenge. These transactions can be represented as dynamic graphs, where Neural Network Convolution (NNConv) models are widely used for detection. However, NNConv models suffer from model decay due to evolving transaction patterns, the introduction of new users, and the emergence of adversarial techniques designed to evade detection. To address this issue, we propose an automated, periodic hyperparameter optimization method based on proximal policy optimization (PPO), a reinforcement learning algorithm designed for dynamic environments. By leveraging PPO’s stable policy updates and efficient exploration strategies, our approach continuously refines hyperparameters to sustain model performance without frequent retraining. We evaluate the proposed method on a large-scale cryptocurrency transaction dataset containing 2,973,489 nodes and 13,551,303 edges. The results demonstrate that our method achieves an F1 score of 0.9478, outperforming existing graph-based approaches. These findings validate the effectiveness of PPO-based optimization in mitigating model decay and ensuring robust cryptocurrency scam detection. Full article

Recently, there have been significant advances and wide-scale use of generative AI in natural language generation. Models such as OpenAI’s GPT3 and Meta’s LLaMA are widely used in chatbots, to summarize documents, and to generate creative content. These advances raise concerns about abuses of these models, especially in social media settings, such as large-scale generation of disinformation, manipulation campaigns that use AI-generated content, and personalized scams. We used stylometry (the analysis of style in natural language text) to analyze the style of AI-generated text. Specifically, we applied an existing authorship verification (AV) model that can predict if two documents are written by the same author on texts generated by GPT2, GPT3, ChatGPT and LLaMA. Our AV model was trained only on human-written text and was effectively used in social media settings to analyze cases of abuse. We generated texts by providing the language models with fanfiction snippets and prompting them to complete the rest of it in the same writing style as the original snippet. We then applied the AV model across the texts generated by the language models and the human written texts to analyze the similarity of the writing styles between these texts. We found that texts generated with GPT2 had the highest similarity to the human texts. Texts generated by GPT3 and ChatGPT were very different from the human snippet, and were similar to each other. LLaMA-generated texts had some similarity to the original snippet but also has similarities with other LLaMA-generated texts and texts from other models. We then conducted a feature analysis to identify the features that drive these similarity scores. This analysis helped us answer questions like which features distinguish the language style of language models and humans, which features are different across different models, and how these linguistic features change over different language model versions. The dataset and the source code used in this analysis have been made public to allow for further analysis of new language models. Full article

Achilles tendon injuries are extremely common and have a significant impact on the physical and mental health of individuals. Both conservative and surgical treatments have unsatisfactory results. The search for new therapeutic tools, using cell therapies with stem cells (SC) and biological tissues, such as amniotic membranes (AM), has proved useful for the regeneration of injured tendons. Background/Objectives: This research was carried out to assess the capacity of tissue repair in animal models of Achilles tendinopathy, in which rats were submitted to complete sections of the tendon, and the effects of using bone marrow SC and/or AM graft are evaluated. Methods: Thirty-seven Wistar rats, submitted to complete surgical section of the Achilles tendon and subsequent tenorrhaphy, were randomized into four groups: Control Group (CG), received saline solution; SC Group (SCG) received an injection of SC infiltrated directly into the tendon; AM Group (AMG), the tendon was covered with an AM graft; SC + AM Group (SC+AMG), has been treated with an AM graft and SC local injection. Six weeks later, the Achilles tendons were evaluated using a histological score and immunohistochemical pro-healing markers such as Interferon-γ, AKT, and mTOR. Results: There were no differences between morphometric histological when evaluating the Achilles tendons of the samples. No significant differences were found regarding the expression of AKT-2 and mTOR markers between the study groups. The main finding was the presence of a higher concentration of Interferon-γ in the group treated with SC and AM. Conclusions: The isolated use of SC, AM, or the combination of SC-AM did not produce significant changes in tendon healing when the histological score was evaluated. Similarly, no difference was observed in the expression of AKT-2 and mTOR markers. An increase in the expression of Interferon-γ was observed in SC+AMG. This suggests that such therapies may be potentially beneficial for the regeneration of injured tendons. However, as tendon repair mechanisms are very complex, further studies should be carried out to verify the benefits of the tendon structure and function. Full article

This study examines cyber sextortion research using a comprehensive bibliometric analysis. In the field of cybersecurity, cyber sextortion is a form of cybercrime that leverages privacy violations to exploit a victim. This study reviewed research developments on cyber sextortion progressively over time by looking at scientific productions, thematic developments, scholars’ contributions, and the future thematic trajectory. A bibliometric approach to analyzing the data was applied, which covered 548 peer-reviewed articles, conference papers, and book chapters retrieved from the Scopus database. Results showed a growth trajectory on various thematic concerns in the cyber sextortion field, which has continued to gain traction since the year 2023. Notably, online child sexual abuse is a growing theme in cyber sextortion research. In addition, among other themes, adolescents, mental health, and dating violence are receiving interest among scholars in this field. Additionally, institutions and prolific scholars from countries such as the United States of America, Australia, and the United Kingdom have established research collaborations to improve understanding in this field. The results also showed that research is observed to be emerging from South Africa and Ghana in the African region. Overall, there is potential for more scientific publications and researchers from Africa to contribute to this growing field. The value this study holds is moving beyond deficit-based approaches to how adolescent youth can be resilient and protected from cyber sextortion. A call for a multidisciplinary approach that moves beyond deficit-based approaches toward resilient and autonomy-based approaches is encouraged so that adolescent youth are protected from exploitation. This approach should focus on investigating proactive and resilience-based interventions informed by individuals’ traits and contexts to aid in building digital resilience in adolescents. Full article

With the rapid development of blockchain technology and the popularity of cryptocurrency, phishing scams pose an increasingly severe threat to the security of cryptocurrency transactions. Existing fraud detection methods have not accurately identified phishing behaviors, especially failing to capture key neighbor information and its impact effectively. To address this problem, we proposed a phishing detection framework based on FAAN-GBM (Feature and Attention Augmented Network with Gradient Boosting Machine), which aims to improve phishing fraud detection effectiveness on the Ethereum platform by further refining the extraction of phishing account features. This framework integrates basic features, transaction features, and interaction features of nodes, optimizes feature aggregation through importance analysis and attention mechanism of neighbor node, and uses autoencoders to deepen the nonlinear expression of node features. Through extensive testing on real Ethereum datasets, FAAN-GBM has demonstrated superior performance over existing methods, effectively improving the identification accuracy of phishing fraud nodes. Full article

The objective of this systematic review (SR) was to select studies on the activity of glycerol as a molecule that induces disease resistance in plants. We sought to evaluate articles deposited in five electronic databases using a search string and predefined inclusion and exclusion criteria. The most studied crops are Arabidopsis thaliana, Glycine max, and Coffea spp. The most commonly cited biotic agents include Pseudomonas syringae, Blumeria graminis, and Colletotrichum higginsianum. Numerous doses of glycerol were studied, and concentrations ranged from 0.004 to 9.21%, with a 3% concentration of glycerol being considered most effective for most plant species, where greater resistance was observed with increased glycerol-3-phosphate (G3P) and decreased oleic acid levels. The main means of application of the product were spraying and immersion. The SR also revealed the evaluation of resistance-inducing genes, such as PR proteins (PR-1, PR2, PR-5, etc.), HPS70, HSP90, SCAM4, and Tapr1, among others. The information collected in this SR helps to understand the state of the art on the use of glycerol as a molecule inducing resistance against biotic stressors to understand the mechanisms involved in most host–pathogen relationships. This information will be useful in plant breeding programs and for growers/producers. Full article