This study describes the optimization of hand gesture recognition on Raspberry Pi 4 technology has advanced over the past years, some computers are now able to compute much more complex problems like ...real-time object detection. But for small devices, optimization is required to run in real-time with acceptable performance in terms of latency and low-cost effect on accuracy. Low latency is a requirement for most technology, especially when integrating real-time object detection as input into Self-Service Technology on Raspberry Pi for the store. This research was conducted on 288 pictures with six types of chosen hand gestures for command inputs that have been configured in the Self-Service Technology as a training dataset. In the experiment carried out with 5 CNN object detection models were used, namely YOLOv3-Tiny-PRN, YOLOv4-Tiny, MobileNetV2-Yolov3-NANO, YOLO-Fastest-1.1, and YOLO-Fastest-1.1-XL. Based on the experiment after optimization, the FPS and inference time metrics have improved performance. The performance improves due to a gained average value of FPS by 3 FPS and a reduced average value of inference time by 119,260 ms. But such an improvement also comes with a reduction in overall accuracy. The rest of the parameters have a reduced score on Precision, Recall, F1-Score, and some for IoU. Only YOLO-Fastest-1.1-XL have an improved value of IoU by about 0.58%. Some improvements in the CNN and dataset might improve the performance even more without sacrificing too much on the accuracy, but it's most likely suitable for another research as a continuation of this topic.
Use of the internet as a trade platform has resulted in a shift in the illegal wildlife trade. Increased scrutiny of illegal wildlife trade has led to concerns that online trade of wildlife will move ...onto the dark web. To provide a baseline of illegal wildlife trade on the dark web, we downloaded and archived 9852 items (individual posts) from the dark web, then searched these based on a list of 121 keywords associated with illegal online wildlife trade, including 30 keywords associated with illegally traded elephant ivory on the surface web. Results were compared with items known to be illegally traded on the dark web, specifically cannabis, cocaine, and heroin, to compare the extent of the trade. Of these 121 keywords, 4 resulted in hits, of which only one was potentially linked to illegal wildlife trade. This sole case was the sale and discussion of Echinopsis pachanoi (San Pedro cactus), which has hallucinogenic properties. This negligible level of activity related to the illegal trade of wildlife on the dark web relative to the open and increasing trade on the surface web may indicate a lack of successful enforcement against illegal wildlife trade on the surface web. El uso del internet como plataforma de comercio ha resultado en un cambio en el mercado ilegal de vida silvestre. El escrutinio incrementado del mercado ilegal de vida silvestre ha resultado en preocupación por que el mercado ilegal de vida silvestre llegue a la red oscura. Para proporcionar una línea base del mercado ilegal de vida silvestre en la red oscura descargamos y archivamos 9,852 objetos (publicaciones individuales) de la red oscura y después los buscamos con base en una lista de 121 palabras clave asociadas con el mercado ilegal de vida silvestre en línea, incluyendo 30 palabras clave asociadas con el marfil de elefante comerciado ilegalmente en la superficie de la red. Los resultados se compararon con objetos conocidos por ser comerciados ilegalmente en la red oscura, en específico el cannabis, la cocaína y la heroína, para comparar la extensión del mercado. De estas 121 palabras clave, cuatro resultaron en aciertos, de los cuales sólo uno estuvo potencialmente conectado con el mercado ilegal de vida silvestre. Este caso único fue la venta y discusión de Echinopsis pachanoi (cactus de San Pedro), que tiene propiedades alucinógenas. Este nivel insignificante de actividades relacionadas con el mercado ilegal de la vida silvestre en la red oscura en comparación con el creciente mercado abierto en la superficie de la red puede indicar una falta de autoridad exitosa en contra del mercado ilegal de vida silvestre en la superficie de la red.
Background and aim
Cryptomarkets—on‐line, anonymous market‐places for illicit goods and services that specialize mainly in drugs—account for a small but rapidly growing share of the illicit drug ...market in many countries. Policy responses so far are based generally on the assumption that their rise will only increase drug harms. In this contribution for debate, we question this assumption.
Methods
We provide a narrative review of the emerging literature connected to drug cryptomarkets. We use MacCoun & Reuter's formula to understand the effect of population‐level increases in use on total harm as depending on the level of harm associated with each unit of use. We then consider the potential for cryptomarkets to increase or decrease the harms and benefits related to each unit of drug use, with specific attention to the quality of drugs sold and the non‐drug‐related harms and benefits for customers.
Results
It is likely that cryptomarkets will increase both the amount and the range of substances that are sold. However, we argue that the effects on harms will depend upon whether cryptomarkets also increase the quality and safety of products that are sold, provide harm‐reducing information to consumers and reduce transactional conflict involved in drug purchasing.
Conclusions
There is an emerging and rapidly growing evidence base connected to the macro and micro harms and benefits of cryptomarkets for drug users. Future researchers should use appropriately matched comparative designs to establish more firmly the differential harms and benefits of sourcing drugs both on‐ and off‐line. While it is unlikely that the on‐line drug trade can be eradicated completely, cryptomarkets will respond to regulation and enforcement in ways that have complex, and sometimes unanticipated, effects on both harms and benefits.
Abstract
Research summary
Darknet marketplaces (DNMs) are global digital marketplaces used primarily to buy and sell illicit drugs online. High rates of adulterated substances have contributed to the ...creation of harm reduction policies by DNM administrators to address growing rates of overdose worldwide. This paper explores the extent to which harm reduction occurs in buyer feedback of Adderall and Oxycodone purchased on AlphaBay and how these comments are impacted by AlphaBay's administrator‐led “harm reduction” policy. This study finds that harm reduction strategies are present in buyer feedback of Oxycodone and Adderall pills, but AlphaBay's policy has very little impact on the preexisting harm reduction communication within buyer feedback.
Policy implications
International policy proposals have placed emphasis on addressing the overdose crisis through harm reduction programs that provide people who use drugs with the necessary services and resources to buy and use drugs safely. There have been very few proposals that have considered how these programs can address the unique setting of buying and using drugs purchased on DNMs. Communication occurring among DNM buyers reveals how harm reduction strategies are being employed by users purchasing drugs from DNMs. In particular, these findings offer insight into the shared experiences of drug buyers in anonymous settings and the strategies they are using to protect one another from overdose and other unwanted side effects often caused by adulterated substances. Understanding these strategies highlights the ways in which street‐based harm reduction programs can extend their services to online environments to assist buyers with making safe and informed decisions when using substances purchased online.
With a growing number of smart interconnected devices and services, managing and controlling network traffic is getting more complicated. Among the network traffic, the Darknet-related one is ...particularly interesting, as it is often used for anonymous and illicit activities that pose cyber security threats. Therefore, designing and developing methods for detecting and categorizing Darknet traffic is essential. Applying Deep Learning (DL) is one of the most suitable options in this case. The main reasons are the ability to process a large amount of data and detect the hidden patterns and relationships in these data. This work proposes a DL architecture based on UNet++, which can detect and categorize anonymous traffic. The core idea of this model is semantic segmentation, which can identify meaningful segments that share some common patterns in given data. Hereby, semantic segmentation is postulated as a possible way to investigate Darknet traffic to find some common and related features instead of widely used Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). According to the results on comparison with other Machine Learning (ML) and DL models, the UNet++ model outperforms the methods with a higher accuracy of 98.19% and 87.27% for Darknet detection and traffic categorization. Our work shows the potential of using UNet++ for network traffic analysis and Darknet traffic detection. We have also demonstrated that more advanced architecture with skip connections and trainable blocks provides more accurate results than pure U-Net, CNN, and other evaluated models.
Detecting plant leaf diseases accurately and promptly is essential for reducing economic consequences and maximizing crop yield. However, farmers' dependence on conventional manual techniques ...presents a difficulty in accurately pinpointing particular diseases. This research investigates the utilization of the YOLOv4 algorithm for detecting and identifying plant leaf diseases. This study uses the comprehensive Plant Village Dataset, which includes over fifty thousand photos of healthy and diseased plant leaves from fourteen different species, to develop advanced disease prediction systems in agriculture. Data augmentation techniques including histogram equalization and horizontal flip were used to improve the dataset and strengthen the model's resilience. A comprehensive assessment of the YOLOv4 algorithm was conducted, which involved comparing its performance with established target identification methods including Densenet, Alexanet, and neural networks. When YOLOv4 was used on the Plant Village dataset, it achieved an impressive accuracy of 99.99%. The evaluation criteria, including accuracy, precision, recall, and f1-score, consistently showed high performance with a value of 0.99, confirming the effectiveness of the proposed methodology. This study's results demonstrate substantial advancements in plant disease detection and underscore the capabilities of YOLOv4 as a sophisticated tool for accurate disease prediction. These developments have significant significance for everyone involved in agriculture, researchers, and farmers, providing improved capacities for disease control and crop protection.
The massive modern technical revolution in electronics, cognitive computing, and sensing has provided critical infrastructure for the development of today’s Internet of Things (IoT) for a wide range ...of applications. However, because endpoint devices’ computing, storage, and communication capabilities are limited, IoT infrastructures are exposed to a wide range of cyber-attacks. As such, Darknet or blackholes (sinkholes) attacks are significant, and recent attack vectors that are launched against several IoT communication services. Since Darknet address space evolved as a reserved internet address space that is not contemplated to be used by legitimate hosts globally, any communication traffic is speculated to be unsolicited and distinctively deemed a probe, backscatter, or misconfiguration. Thus, in this paper, we develop, investigate, and evaluate the performance of machine-learning-based Darknet traffic detection systems (DTDS) in IoT networks. Mainly, we make use of six supervised machine-learning techniques, including bagging decision tree ensembles (BAG-DT), AdaBoost decision tree ensembles (ADA-DT), RUSBoosted decision tree ensembles (RUS-DT), optimizable decision tree (O-DT), optimizable k-nearest neighbor (O-KNN), and optimizable discriminant (O-DSC). We evaluate the implemented DTDS models on a recent and comprehensive dataset, known as the CIC-Darknet-2020 dataset, composed of contemporary actual IoT communication traffic involving four different classes that combine VPN and Tor traffic in a single dataset covering a wide range of captured cyber-attacks and hidden services provided by the Darknet. Our empirical performance analysis demonstrates that bagging ensemble techniques (BAG-DT) offer better accuracy and lower error rates than other implemented supervised learning techniques, scoring a 99.50% of classification accuracy with a low inferencing overhead of 9.09 µ second. Finally, we also contrast our BAG-DT-DTDS with other existing DTDS models and demonstrate that our best results are improved by (1.9~27%) over the former state-of-the-art models.
The rise of the darknet market, supported by technologies such as the Tor Browser and cryptocurrencies, has created a secure environment in which illicit transactions can occur. However, due to the ...lack of government oversight in this hidden online domain, darknet markets face significant challenges in upholding social order. Hence, this study explores the social dynamics that promote social order in a darknet market, focusing on the impact of item descriptions on sales. In particular, the study examines how text contained in product listings can influence sales and contribute to social order.
To conduct this analysis, we examined 4160 cocaine listings on AlphaBay, which was active from December 2014 to July 2017 and is one of the largest darknet markets in history. Using generalised additive models (GAMs), we assessed the impact of various listing description features, including content and semantic structure, on cocaine sales.
The results showed that sales increased by 61.6 % when listings included delivery information in their description, compared to offers that did not. In addition, the standardised sentiment score (ranging 0,1) of the product description increased positively, and estimated sales increased by 260.5 %. We also found that international shipping reduced sales by 28.3 %. Finally, we found that listings stating the product origin increased sales for all continents except Asia.
The study sheds light on the characteristics of product advertising that facilitate social order within a darknet market. Listings that include delivery details in the description reduce uncertainty about a critical stage of the transaction process while using positive language increases trust. This study makes both an empirical and a theoretical contribution by demonstrating the influence of ad descriptions on sales and the intricate role of social influences in shaping market order.
Towards a Conceptual Typology of Darknet Risks Ogbanufe, Obi; Wolfe, Jordan; Baucum, Fallon
The Journal of computer information systems,
07/2024, Letnik:
ahead-of-print, Številka:
ahead-of-print
Journal Article
Recenzirano
Increased rewards and reduced risks drive illicit networks. Cybercriminals seek to avoid risks, including detection, arrests, sanctions, and violence. Hence, they employ several strategies to avoid ...operational risks when accessing darknet sites, communicating, making payments, shipping and delivery, and resolving disputes. Each operation involves transactions that should work together, such that when a transaction is disrupted, it increases its risk and reduces the crime's benefits. In this study, we examine these risks, and their avoidance strategies, in an attempt to highlight transactions that could be disrupted. We develop a typology of darknet risks, a parsimonious conceptual model abstracted from the literature on risk originators (internal or external) and risk targets (vendors or buyers). This study further clarifies how risk avoidance strategies may be disrupted to increase the risks and reduce the reward of darknet crime.
Today, the Internet security community largely emphasizes cyberspace monitoring for the purpose of generating cyber intelligence. In this paper, we present a survey on darknet. The latter is an ...effective approach to observe Internet activities and cyber attacks via passive monitoring. We primarily define and characterize darknet and indicate its alternative names. We further list other trap-based monitoring systems and compare them to darknet. Moreover, in order to provide realistic measures and analysis of darknet information, we report case studies, namely, Conficker worm in 2008 and 2009, Sality SIP scan botnet in 2011, and the largest amplification attack in 2014. Finally, we provide a taxonomy in relation to darknet technologies and identify research gaps that are related to three main darknet categories: deployment, traffic analysis, and visualization. Darknet projects are found to monitor various cyber threat activities and are distributed in one third of the global Internet. We further identify that Honeyd is probably the most practical tool to implement darknet sensors, and future deployment of darknet will include mobile-based VOIP technology. In addition, as far as darknet analysis is considered, computer worms and scanning activities are found to be the most common threats that can be investigated throughout darknet; Code Red and Slammer/Sapphire are the most analyzed worms. Furthermore, our study uncovers various lacks in darknet research. For instance, less than 1% of the contributions tackled distributed reflection denial of service (DRDoS) amplification investigations, and at most 2% of research works pinpointed spoofing activities. Last but not least, our survey identifies specific darknet areas, such as IPv6 darknet, event monitoring, and game engine visualization methods that require a significantly greater amount of attention from the research community.