Search

Throughout the annals of history, governments and their central banks have been alleged to breach trust through the manipulation of funds and the debasement of fiat currencies. Cryptocurrencies, with their underpinning blockchain technology, have revolutionized and democratized the modern finance ecosystem. Their digital, decentralized, and unregulated nature has catalyzed a paradigm shift, disrupting the conventional banking system and empowering individuals with direct and absolute control over their assets. Concurrently, cryptocurrencies can be extremely arduous to wrap one’s head around, especially when shrouded with an intricate web of technobabble and algorithmic complexities. The realm of cryptocurrencies, akin to diverse social media platforms, presents a plethora of formidable challenges and inherent dangers. With the incessant advent of new cryptocurrencies, the proliferation of illicit activities has become rampant, posing a grave threat to the crypto community. Crypto trading/investing entails a high-risk endeavor that could jeopardize the entire investment. This article demystifies the underlying perils that engulf the crypto world.

This paper presents DeepCKID, a Multi-Head Attention (MHA)-based deep learning model that exploits statistical and semantic knowledge corresponding to documents across different classes in the datasets to improve the model’s ability to detect minority class instances in imbalanced text classification. In this process, corresponding to each document, DeepCKID extracts — (i) word-level statistical and semantic knowledge, namely, class correlation and class similarity corresponding to each word, based on its association with different classes in the dataset, and (ii) class-level knowledge from the document using n-grams and relation triplets corresponding to classwise keywords present, identified using cosine similarity utilizing Transformers-based Pre-trained Language Models (PLMs). DeepCKID encodes the word-level and class-level features using deep convolutional networks, which can learn meaningful patterns from them. At first, DeepCKID combines the semantically meaningful Sentence-BERT document embeddings and word-level feature matrix to give the final document representation, which it further fuses to the different classwise encoded representations to strengthen feature propagation. DeepCKID then passes the encoded document representation and its different classwise representations through an MHA layer to identify the important features at different positions of the feature subspaces, resulting in a latent dense vector accentuating its association with a particular class. Finally, DeepCKID passes the latent vector to the softmax layer to learn the corresponding class label. We evaluate DeepCKID over six publicly available Amazon reviews datasets using four Transformers-based PLMs. We compare DeepCKID with three approaches and four ablation-like baselines. Our study suggests that in most cases, DeepCKID outperforms all the comparison approaches, including baselines.

The extensive use of digital devices by individuals generates a significant amount of private data which creates challenges for investigation agencies to protect suspects' privacy. Existing digital forensics models illustrate the steps and actions to be followed during an investigation, but most of them are inadequate to investigate a crime with all the processes in an integrated manner and do not protect suspect's privacy. In this paper, we propose the development of a privacy-preserving digital forensics (P2DF) framework, which facilitates investigation through maintaining confidentiality of the suspects through various privacy standards and policies. It includes an access control mechanism which allows only authorized investigators to access private data and identified digital evidences. It is also equipped with a digital evidence preservation mechanism which could be helpful for the court of law to ensure the authenticity, confidentiality, and reliability of the evidences, and to verify whether privacy of the suspect was preserved during the investigation process.

Digital forensics science is a well-known initiative to unearth computer-assisted crimes. The thriving criminal activities using digital media have changed the typical definition of a traditional crime. Meanwhile, the means and targets of criminal activities have been transformed in a broader context due to the diverse nature of offenses associated with the multiple crime categories, affecting the way of investigations as well. In order to withstand the difficulties caused due to the crime complexity, forensics investigation frameworks are being tuned to adjust with the nature and earnestness of the felonies being committed. This article presents an in-depth comparative survey of fourteen popular and most cited digital forensics process models and various forensics tools associated with different phases of these models. The relationships among these forensics process models and their evolutions are analyzed and a graph-theoretic approach is presented to rank the existing process models to facilitate investigators in selecting an appropriate model for their investigation tasks.

As the online social network technology is gaining all time high popularity and usage, the malicious behavior and attacks of spammers are getting smarter and difficult to track. The newer spamming approaches using the social engineering concepts are making traditional spam and spammer detection techniques obsolete. Especially, content-based filtering of spam messages and spammer profiles in online social networks is becoming difficult. Newer approaches for spammer detection using topological features are gaining attention. Further, the evaluation of ensemble classifiers for detection of spammers over social networking behavior-based features is still in its infancy. In this paper, we present an ensemble learning method for online social network security by evaluating the performance of some basic ensemble classifiers over novel community-based social networking features of legitimate users and spammers in online social networks. The proposed method aims to identify topological and community-based features from users’ interaction network and uses popular classifier ensembles – bagging and boosting to identify spammers in online social networks. Experimental evaluation of the proposed method is done over a real-world data set with artificial spammers that follow a behavior as reported in earlier literature. The experimental results reveal that the identified features are highly discriminative to identify spammers in online social networks.

Tag clouds have become an effective tool to quickly perceive the most prominent terms embedded within textual data. Tag clouds help grasp the main theme of a corpus without exploring the pile of documents. However, the effectiveness of tag clouds to conceptualize text corpora is directly proportional to the quality of the tags. In this paper, the authors propose a keyphrase-based tag cloud generation framework. In contrast to existing tag cloud generation systems that use single words as tags and their frequency counts to determine the font size of the tags, the proposed framework identifies feasible keyphrases and uses them as tags. The font-size of a keyphrase is determined as a function of its relevance weight. Instead of using partial or full parsing, which is inefficient for lengthy sentences and inaccurate for the sentences that do not follow proper grammatical structure, the proposed method applies n-gram techniques followed by various heuristics-based refinements to identify candidate phrases from text documents. A rich set of lexical and semantic features are identified to characterize the candidate phrases and determine their keyphraseness and relevance weights. The authors also propose a font-size determination function, which utilizes the relevance weights of the keyphrases to determine their relative font size for tag cloud visualization. The efficacy of the proposed framework is established through experimentation and its comparison with the existing state-of-the-art tag cloud generation methods.