The authentication textual passwords are the most widely used technique. However, this type of legacy authentication is vulnerable to various attacks, such as shoulder-surfing attacks. Hence, graphical password authentication is one of these approaches which has been suggested to overcome the issues related to textual passwords. Nevertheless, the hackers have also developed new techniques that can be finally broken the graphical password, for instance, listening to the transmitted information between the client and the server. In this paper, Passnumbers graphical authentication password is proposed. Passnumbers approach involves two new stages, which are first, using the coordinates of a graphical grid cells-based numbers for entering the password. The second stage is represented by deploying a new technique to encrypt the password based on the image pixels. The performance evaluation reveals that the proposed Passnumbers can provide high resistance against several graphical password attacks including shoulder surfing and eavesdropping attacks. Passnumbers is evaluated using several metrics including security and usability.
The security of a PIN is largely supported by the authentication process in ATM. Most authentication methods like traditional are based on using PIN as direct entry and this technique has been shown lots of drawbacks such as vulnerability to password space, and shoulder-surfing. In this paper, a new approach is proposed called RoundPIN depends on the appearance of the numerical password through one of the buttons after selecting it by the user and it is done through a number of rounds, the numbers are arranged randomly on the keypad. Due to the variable aspect of the chosen button and the random appearance of the numbers in each connection session and also the selection process will take place through three buttons three auxiliary, the proposed approach can maintain high secure session to enter the PIN to resist shoulder surfing, which is difficult for attackers to observe a user's PIN. The performance evaluation of the proposed approach is achieved in two parts, the first one is based on security analysis. Then a pilot study of thirty users is conducted to evaluate the useability of the proposed approach. It is noticed that the proposed approach can maintain a high level of security as well as acceptable level of useability and user satisfaction compared the conventional keypad system.
<p>Predictive maintenance (PdM) is a cost-cutting method that involves avoiding breakdowns and production losses. Deep learning (DL) algorithms can be used for defect prediction and diagnostics due to the huge amount of data generated by the integration of analog and digital systems in manufacturing operations. To improve the predictive maintenance strategy, this study uses a hybrid of the convolutional neural network (CNN) and conditional generative adversarial neural network (CGAN) model. The proposed CNN-CGAN algorithm improves forecast accuracy while substantially reducing model complexity. A comparison with standalone CGAN utilizing a public dataset is performed to evaluate the proposed model. The results show that the proposed CNN-CGAN model outperforms the conditional GAN (CGAN) in terms of prediction accuracy. The average F-Score is increased from 97.625% for the CGAN to 100% for the CNN-CGAN.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.