The problem of imbalanced datasets is a significant concern when creating reliable credit card fraud (CCF) detection systems. In this work, we study and evaluate recent advances in machine learning (ML) algorithms and deep reinforcement learning (DRL) used for CCF detection systems, including fraud and non-fraud labels. Based on two resampling approaches, SMOTE and ADASYN are used to resample the imbalanced CCF dataset. ML algorithms are, then, applied to this balanced dataset to establish CCF detection systems. Next, DRL is employed to create detection systems based on the imbalanced CCF dataset. The diverse classification metrics are indicated to thoroughly evaluate the performance of these ML and DRL models. Through empirical experiments, we identify the reliable degree of ML models based on two resampling approaches and DRL models for CCF detection. When SMOTE and ADASYN are used to resampling original CCF datasets before training/test split, the ML models show very high outcomes of above 99% accuracy. However, when these techniques are employed to resample for only the training CCF datasets, these ML models show lower results, particularly in terms of logistic regression with 1.81% precision and 3.55% F1 score for using ADASYN. Our work reveals the DRL model is ineffective and achieves low performance, with only 34.8% accuracy.

Nowadays, biometrics‐based authentication is playing a potential approach for many modern applications such as banking, homeland security etc. However, the end‐users may feel uncomfortable to deploy this technology because of not well‐solved accurate rate and security problems. To overcome these issues, some significant techniques have been proposed such as biometric template protection, reducing biometric extraction noise etc. Fuzzy vault is one of the most popular methods for biometric template security, which binds a secret key with biometric features and produces one kind of data, called the helper data, for recovering the secret key. Unfortunately, the major drawback of this approach is the lacking of cancellable property. Furthermore, most of the fuzzy vault schemes are performed on two biometrics modalities: fingerprints and iris. Some techniques were introduced to transform the original biometric feature to cancellable one. However, the computational cost of these proposals was quite large. In this research, the authors introduce a periodic transformation attached to fuzzy vault to produce the new cancellable scheme. Their transformation is not only simpler but also suitable for many kinds of biometrics modalities. The experiments demonstrate that this approach is practical with a little better error rate in comparison with the original biometric feature.

Since the last decade, we have seen an increasing level of interest in time series data mining due to its variety of real-world applications. Numerous representation models of time series have been proposed for data mining, including piecewise polynomial models, spectral models, and the recently proposed symbolic models, such as Symbolic Aggregate approXimation (SAX) and its multiresolution extension, indexable Symbolic Aggregate approXimation (iSAX). In spite of many advantages of dimensionality/numerosity reduction, and lower bounding distance measures, the quality of SAX approximation is highly dependent on the Gaussian distributed property of time series, especially in reduced-dimensionality literature. In this paper, we introduce a novel adaptive symbolic approach based on the combination of SAX and k¬-means algorithm which we call adaptive SAX (aSAX). The proposed representation greatly outperforms the classic SAX not only on the highly Gaussian distribution datasets, but also on the lack of Gaussian distribution datasets with a variety of dimensionality reduction. In addition to being competitive with, or superior to, the classic SAX, we extend aSAX to the multiresolution symbolic representation called indexable adaptive SAX (iaSAX). Our empirical experiments with real-world time series datasets confirm the theoretical analyses as well as the efficiency of the two proposed algorithms in terms of the tightness of lower bound, pruning power and number of random disk accesses.

Attribute-based access control (ABAC) model manages access control through policies, based on incoming requests in which attributes are basic elements for constructing those policies and requests. Requests depend on existing policies in the system and when policies change attributes, request must be adapted to access resources. In XACML standard, there are four kinds of responses for a request: Permit, Deny, Not Applicable and Indeterminate, but the two last value bring no value to requesters. This paper focuses on rewriting requests received Not Applicable responses by reducing required resource for aligning with policies of systems. We set up a new model based on XACML 3.0 find out the most suitable policy to each input request in four aspects, including Action, Subject, Environment, and Resource to rewrite the request. Finally, the model is implemented based on AT&T Open Source. We use an XACML 3.0 framework, for verifying feasibility of the solution and measuring its performance.