Explore the vast range of titles available.

Credit card (CC) fraud has been a persistent problem and has affected financial organizations. Traditional machine learning (ML) algorithms are ineffective owing to the increased attack space, and techniques such as long short-term memory (LSTM) have shown promising results in detecting CC fraud patterns. However, owing to the black box nature of the LSTM model, the decision-making process could be improved. Thus, in this paper, we propose a scheme, RaKShA, which presents explainable artificial intelligence (XAI) to help understand and interpret the behavior of black box models. XAI is formally used to interpret these black box models; however, we used XAI to extract essential features from the CC fraud dataset, consequently improving the performance of the LSTM model. The XAI was integrated with LSTM to form an explainable LSTM (X-LSTM) model. The proposed approach takes preprocessed data and feeds it to the XAI model, which computes the variable importance plot for the dataset, which simplifies the feature selection. Then, the data are presented to the LSTM model, and the output classification is stored in a smart contract (SC), ensuring no tampering with the results. The final data are stored on the blockchain (BC), which forms trusted and chronological ledger entries. We have considered two open-source CC datasets. We obtain an accuracy of 99.8% with our proposed X-LSTM model over 50 epochs compared to 85% without XAI (simple LSTM model). We present the gas fee requirements, IPFS bandwidth, and the fraud detection contract specification in blockchain metrics. The proposed results indicate the practical viability of our scheme in real-financial CC spending and lending setups.

One of the telecommunications’ most popular forms of fraud is the short message service (SMS). Mobile users have a valid fear about SMS spam, which disturbs telecoms network operators since it impacts their clients and costs them money. For that, the existing research utilized an artificial intelligence approach to detect SMS phishing in telecommunication. Since SMS text data is unstructured and contains complicated, nonlinear relationships, this process could be difficult. Therefore, this research developed a Fraud Resilient Framework using Enhanced CNN-based SMS Phishing detection. Telecommunication fraud-related datasets are collected. Firstly, the data are preprocessed and cleaned using stemming, tokenization, and the TF-IDF approach. Moreover, to extract the features, the existing research utilized the information gain technique, which is time-consuming. So to overcome these flaws, this research introduces Assimilated Pearson Correlation Coefficient Principal Component Analysis (PCC-PCA) for feature extraction. This research introduces an enhanced Convolutional Neural Network (Enhanced CNN) in which, overcome the exploding gradients, this research introduces Parameterized ReLU which minimizes architecture complexity, regularizing, and early stopping. Then, the retrieved features are used in Enhanced CNN to categorize the ham and spam in the telecommunication network. As a result, when matched to cutting-edge techniques, this proposed solution offers great accuracy and efficiency.

The US National Academy of Sciences' report, On Being a Scientist: Responsible Conduct in Research distinguishes clearly between \"misallocation of credit, honest errors, and errors caused through negligence\" and \"deception, making up data or results, changing or misreporting data or results, and plagiarism\". The White House's Office of Science and Technology Policy reached similar conclusions, restricting research misconduct to \"fabrication, falsification and plagarism\".

There is no denying electronic auditing software that flags potentially fraudulent claims has its role. Yet with the many advantages that the technology brings for government oversight of claims, some consideration must be given to how the software is being used and the potential for undesirable effects - particularly for providers. The software analysis, though useful for investigation, should not be treated as evidence of fraud. Electronic auditing and its heightened level of review can present a challenge for providers. Providers must trust that government auditors will not report simple errors to law enforcement, but will resolve most issues administratively.