User Authentication Research Articles

Integrating NLP Chatbot into Career Guidance Web Application

Artificial Intelligence (AI) is the development of computer systems that can perform tasks that typically require human intelligence. The development of an advanced web-based chatbot system involves the integration of various technologies and methodologies to create a seamless conversational interface. Leveraging HTML, CSS, and JavaScript for frontend development, alongside Python Flask framework for backend functionality, the project aims to deliver a robust and intuitive user experience. Key to the system's operation is the incorporation of PyTorch for machine learning, allowing for the implementation of sophisticated natural language processing (NLP) techniques. Through tokenization and stemming using NLTK (Natural Language Toolkit), the system enhances its understanding of user queries, enabling it to provide relevant and contextually appropriate responses. At the core of the system lies a supervised learning model trained on a custom dataset compiled from user interactions. This model utilizes bag-of-words representations and neural network architectures to predict responses based on input text. By continuously refining its predictions through feedback mechanisms, the system improves its accuracy and responsiveness over time, ensuring a more tailored and effective user experience. Voice input functionality, facilitated by speech recognition technology, further enhances user interaction by allowing users to communicate with the chatbot using spoken commands. This feature expands the accessibility and convenience of the system, catering to a broader range of users with varying preferences and abilities. In addition to its conversational capabilities, the system prioritizes security and privacy, implementing robust user authentication mechanisms and secure data storage practices. By adhering to industry best practices and standards, the project aims to instill trust and confidence in users regarding the confidentiality and integrity of their data.User interface design and usability are also key considerations in the development process, with careful attention given to creating an intuitive and visually appealing interface. Through thoughtful design choices and user feedback, the system seeks to optimize the user experience and streamline the interaction flow, ensuring that users can easily navigate and utilize its features. Overall, the project endeavors to create an intelligent and user-friendly chatbot system that enhances communication and interaction between users and technology. By leveraging advanced technologies and methodologies, the system aims to provide personalized assistance and support to users, ultimately improving productivity, efficiency, and satisfaction in various domains and applications

A multiple-image encryption method based on bimodal biometric keys

In this paper, a multiple-image encryption method based on bimodal biometric keys is proposed, which has the advantages of high level of security, high encryption efficiency, high security and good convenience as well as strong robustness of bimodal biometric keys. In the encryption process, each plaintext image is firstly encoded into corresponding QR code and subsequently encrypted by using a compressive encryption method with fingerprint chaotic measurement matrix of each encryption user and a filtering encryption method in discrete cosine transform domain with iris chaotic mask of each encryption user successively, then the encryption complex amplitude is generated with the help of grating modulation technology and matrix splicing technology, thereafter the encryption complex amplitude is finally encrypted into two hologram ciphertexts by using a two-step phase-shift digital holography with fingerprint chaotic phase mask of encryption administrator. In the decrytion process, the decryption administrator first passes the fingerprint authentication and then the decryption complex amplitude is generated, thereafter multiple-image decryption can be achieved through the fingerprint authentication and iris authentication of each decryption user. In order to demonstrate the feasibility of the proposed multiple-image encryption method, a series of numerical simulations are performed, and the simulation results show that the proposed method exhibits high feasibility as well as level of security and the bimodal biometric keys possess high security and strong robustness.

Optimized Transfer Learning Based Dementia Prediction System for Rehabilitation Therapy Planning

Abstract: Dementia is a progressive neurodegenerative disease leading to cognitive decline, and current medical interventions can only slow its progression. Early prediction of dementia onset holds potential for preventive measures. This study aims to develop a machine learning model using transfer learning from magnetic resonance imaging (MRI) data to predict dementia. The project employs k-fold cross-validation and various parameter optimization algorithms during model training to enhance prediction accuracy. The final voting classifier and optimized Transfer Learning algorithms achieved an impressive accuracy, surpassing the performance of competing methods on the same dataset. This suggests the efficacy of the proposed transferlearning approach in predicting dementia data. The developed model enables early diagnosis of dementia, a crucial factor in halting neurological deterioration associated with the disease. This is particularly relevant for regions with limited access to human physicians, providing a valuable tool for underserved populations. The proposed system holds promise for planning rehabilitation therapy programs for dementia patients. As a tool for early diagnosis and intervention, the model not only contributes to improved patient outcomes but also addresses the challenges faced by regions lacking access to sufficient healthcare resources. And also include ensemble methods (Voting Classifier, Stacking Classifier) and a hybrid CNN-LSTM approach are employed for improving accuracy, with the Voting Classifier achieving an impressive 100% accuracy. To facilitate user testing, a user-friendly front end using the Flask framework, incorporating user authentication, was proposed for seamless application of this advanced dementia prediction system.

Enhanced Road Safety through Integrated Speed Breaker, Pothole, and Lane Detection System

Abstract: Amidst the rapid evolution of autonomous vehicle technologies, ensuring road safety remains a paramount challenge. Effective detection of lanes and potential hazards, including speed breakers and potholes, is critical for safe autonomous driving. In this study, we introduce an innovative Lane, Speed Breaker, and Pothole Detection System (LSPDS) utilizing YOLOv4 Tiny, a state-of-the-art object detection algorithm and computer vision techniques. Our system integrates computer vision and machine learning techniques for analysis of road conditions. By employing camera sensors, we capture the road scene and apply image processing algorithms to identify lanes, speed breakers, and potholes. Moreover, the system incorporates Firebase for user authentication and SMS services for real-time alerts. YOLOv4 Tiny is employed for accurate detection and classification of these features within the captured images, thereby enhancing the perception capabilities of autonomous vehicles.

A Recognition-Based Graphical Password System for Enhanced User Authentication

Abstract: Password-based authentication is a popular way for ensuring computer application security and privacy. Nonetheless, the "weakest link" in the authentication process is believed to be user-chosen weak passwords and hazardous input techniques. People generally utilize mnemonic or brief passphrases instead of random alphanumeric characters. Because internet and mobile applications are widely available, users can access them from any location, at any time, using any device. While this simplicity is generally appreciated, it also increases the likelihood that credentials will be compromised through Visual Hacking. The assault tactics can include employing external recording equipment or watching the victim personally in order to obtain their login information. In response to this issue, our team created a graphical password-based authentication mechanism to combat the threat of Visual Hacking. The system's security mechanism is three-tiered, featuring password verification as well as colour and pattern matching features. This means that even with numerous camera-based hacking attempts, potential attackers would have a tough time determining or limiting the password. In addition, we created and tested a system prototype to determine its usability. According to our trial results, our system can survive Visual Hacking better than previous authentication systems while maintaining a high level of security and usability.

An Intelligent Cryptographic Approach for Preserving the Privacy and Security of Smart Home IoT Applications

Background:: Today, computer networks are everywhere, and we utilize the Internet to access our home network. IoT networks connect home appliances and provide remote instructions. Access to any tool over an uncertain network attracts assaults. User authentication might be password- or biometric-based. Data security across a secure network like the Internet is difficult when authenticating a device. Hashing is used for validation and confidentiality in several encryption and decryption schemes. Classic cryptographic security methods require a lot of memory, processing power, and power. They cannot work with low-resource IoT devices. Method:: Automatic Device-to-Device communiqué opens up new applications, yet network machines and devices have limited resources. A remote-access home device authentication mechanism is proposed in this research. A new, lightweight encryption approach based on Deoxyribonucleic- Acid (DNA) sequences is developed to make IoT device connections easy and secure. Home network and appliance controller devices use authentication tools. DNA sequences are random therefore we utilized them to create a secure secret key. Results:: Efficiency and strength are advantages of the proposed method. Our method prevents replay, server spoofing, and man-in-the-middle attacks. The suggested method protects network users and devices. Conclusion:: Meanwhile, we model the system and find that the network's delay, throughput, and energy consumption don't degrade considerably.

Application of form honeypot based on CSS style in ticket booking system

Since various means of transportation and entertainment activities are restricted by objective conditions, the number of tickets is always limited, so ticket scalpers continue to be a companion product to this day. In the current Internet environment, the web application of the ticketing system faces challenges from ticket-grabbing robots controlled by ticket dealers. The current security procedures have significantly increased the workload and time consumption of effective users. The question now is whether ticket-grabbing bots can be stopped without increasing the workload of legitimate users and being as unnoticed by users as possible. In response to this problem, this article proposes a ticket booking system model integrated with a form-based honeypot, which can achieve the function of deceiving robots without being noticed by ordinary users. This model provides a feasible method for implementing network applications that are both secure and efficient, ensuring that users have a more seamless and protected experience.

ONE3A: one-against-all authentication model for smartphone using GAN network and optimization techniques.

This study focuses on addressing computational limits in smartphones by proposing an efficient authentication model that enables implicit authentication without requiring additional hardware and incurring less computational cost. The research explores various wrapper feature selection strategies and classifiers to enhance authentication accuracy while considering smartphone limitations such as hardware constraints, battery life, and memory size. However, the available dataset is small; thus, it cannot support a general conclusion. In this article, a novel implicit authentication model for smartphone users is proposed to address the one-against-all classification problem in smartphone authentication. This model depends on the integration of the conditional tabular generative adversarial network (CTGAN) to generate synthetic data to address the imbalanced dataset and a new proposed feature selection technique based on the Whale Optimization Algorithm (WOA). The model was evaluated using a public dataset (RHU touch mobile keystroke dataset), and the results showed that the WOA with the random forest (RF) classifier achieved the best reduction rate compared to the Harris Hawks Optimization (HHO) algorithm. Additionally, its classification accuracy was found to be the best in mobile user authentication from their touch behavior data. WOA-RF achieved an average accuracy of 99.62±0.40% with a reduction rate averaging 87.85% across ten users, demonstrating its effectiveness in smartphone authentication.

Implementasi Authentication Captive Portal Pada Wireless Local Area Network di PT. St. Morita Industries

PT. St. Morita Industries has a Wireless Local Area Network (WLAN) which is used as a medium for exchanging data and information by utilizing wireless transmission media, WLAN currently uses WPA2-PSK as a security system to authenticate users to access the internet. However, the use of WPA2-PSK as WLAN security still has a weakness due to the use of the same 1 password for many users in order to connect to the WLAN hotspot will be an opportunity for cyber crime. This happens because it will be very easy for irresponsible users to enter the WLAN. Therefore, in this study, captive portal authentication will be applied as an effort to increase WLAN security replaces WPA2-PSK. This research process uses the Network Development Life Cycle (NDLC) method. All the configurations needed to build the captive portal authentication take advantage of the Winbox program. This research has resulted in a special user authentication limitation for users who have registered on the WLAN is permitted to access this company's internet. In addition, the Winbox program can also be used for monitoring all users connected to the WLAN, both active and inactive users. By setting up captive portal authentication on a WLAN network using a proxy routerboard device which comprises an IP address, DHCP server, hostpot setup, NAT firewall, and DNS server one can create a WPA2-PSK security system. This configuration is completed with the aid of the Winbox v3.37 software.

MORSE CODE-BASED AUTHENTICATION SYSTEM

To tackle analytically complex issues, data science is a multidisciplinary combination of data inference, algorithm development, and technology. Nearly every industry, including business, finance, healthcare, and education, uses data science to manage massive volumes of data. Practical uses include text prediction, image processing, identity recognition, audio processing for speech, stock movement, and cancer prediction. Given that the majority of individuals on the planet have issues with security and authentication, For those who use Morse Code for self-authentication, we can offer real-time eye tracing for password authentication. As we all know, the 21st century has seen significant support for advancements in authorization and authentication technology. Since the late 1990s, personal identification numbers, or PINs, have been extensively used for user authentication and security. These days, it is easy to crack PIN codes, so we would rather use a different strategy. On the other hand, PIN authentication using hands-off gaze-based PIN entry techniques offers a more secure password entry option because it leaves no physical traces behind. Key Words: Morse code, Face recognition, Pin Entry, Eye Blinks, Gaze based

LEARNING MANAGEMENT SYSTEM

In order to revolutionize education, our research paper explores the development and implementation of a revolutionary Learning Management System (LMS). LMS platforms play a key role in contemporary education by acting as virtual centers of instruction. In this article, we examine the essential features of our learning management system (LMS), including content management and user authentication, which improve resource accessibility and expedite instructional procedures. By employing an agile development methodology, we made sure that stakeholders were included at every stage of the project's development. We also talk about the concrete advantages that our LMS provides, such better teaching results and an improved user experience. Our study highlights the transformative potential of our learning management system (LMS) in creating inclusive and stimulating learning environments for all students by highlighting the significance of technology in education. Keywords— Digital Education, Education Technology, Progress Tracking, Accessibility in Education, User Authentication

Implementation on Fake Instagram Profile Identification and Classification Using Machine Learning

Fake Instagram profiles are a growing problem, as they can be used to spread false information, deceive people, and harass and threaten others. The project aims to develop a robust and scalable system for identifying and classifying fake Instagram profiles using machine learning. This system will collect a large and diverse dataset of Instagram profiles, both real and fake. The data will be preprocessed and cleaned, and then relevant features will be extracted. Various machine learning algorithms will be evaluated to select the best model for identifying and classifying fake Instagram profiles. The trained model will be evaluated on a hold-out test set to ensure that it is able to generalize to new data. Once the model is evaluated and deemed satisfactory, it will be deployed in a production environment to identify and classify fake Instagram profiles in real time. The system is expected to have a significant impact on the fight against fake Instagram profiles. By identifying and classifying fake Instagram profiles, the system can help make the social media platform safer and more secure for everyone.. Key Words: Profile identification, Data preprocessing, Online security, User authentication, Model training, Machine learning.

Enhancing Students Experience: A Comprehensive Approach through Uni-Connect

In today's digital age, university students seek comprehensive platforms that transcend basic functionalities to enrich their academic, professional, and social experiences. Inspired by this need, we propose the development of UniConnect, a dynamic web application utilizing the MERN stack. UniConnect serves as a centralized hub offering a plethora of features including user authentication, profile management, event management, job placement, real- time notifications, resource hub, project collaboration tools, peer tutoring, career assessments, and more. This paper outlines the phased development approach undertaken to realize UniConnect's vision, culminating in three distinct phases: Basic, Intermediate, and Advanced versions. Each phase incrementally enhances the platform's capabilities, focusing on functionality, usability, and user engagement. Evaluation results demonstrate the effectiveness of the UniConnect platform in meeting the diverse needs of university students, fostering collaboration, networking, and personal development. Through UniConnect, we aim to revolutionize the university experience, empowering students to thrive academically, professionally, and socially.

Enhanced Local Binary Pattern Algorithm for Facial Recognition Using Chinese Remainder Theorem

Current biometrics research focuses on achieving a high authentication success rate for identity management and discussing the threat  of various security attacks. Local Binary Pattern (LBP), one of the methods for feature extraction, and Chicken Swarm Optimization (CSO),  one of the strategies for feature selection, were used for user identification and authentication. LBP requires high computational time to  extract features from the facial images. The Chinese Remainder Theorem (CRT) was used to reduce its computational time by formulating  an Enhanced Local Binary Pattern (ELBP). Michael Olugbenga Banji Abolarinwa (MOBA) database was created specifically for  this study. 600 frontal facial images of 200 people were collected, each with three images. 360 images were used for training while  240 images were used for testing. MATLAB (R2016a) was used to run the simulation. The time it took to classify the facial images when  LBP and CSO were combined and when ELBP and CSO were combined were enumerated. The LBP-CSO achieved a false-positive rate  (FPR) of 11.67%, a sensitivity (SEN) of 92.78%, a specificity (SPEC) of 88.33%, a precision (PREC) of 95.98%, and an accuracy of 91.67% in  119.10 seconds at 0.80 thresholds for face recognition. ELBP-CSO obtained an FPR of 5.00%, SEN of 95.00%, SPEC of 95.00%, PREC of  98.28%, and accuracy of 95.00% in 79.16 seconds. The results showed that LBP-CSO took an average of 119.10 seconds and ELBP-CSO took  an average of 79.16 seconds. In conclusion, the performance of CSO-ELBP justifies the usage of LBP enhancement with CRT. 

SEAF-IoD: Secure and efficient user authentication framework for the Internet of Drones

The Internet of Drones (IoD) stands as a rapidly advancing technology, finding applications across civilian, military, and industrial domains, facilitating the efficient execution of challenging tasks. However, the IoD environment introduces a plethora of security concerns. Drones, for example, must exchange critical information with control station servers and users through open and unsecured wireless channels. Consequently, protecting these sensitive data becomes paramount, leading to the development of SEAF-IoD, a secure and efficient user authentication framework for the IoD, as presented in this paper. SEAF-IoD relies on symmetric encryption, physical uncloneable functions (PUF), and hash functions. This framework empowers users to securely establish connections and obtain real-time data from specific drones deployed within the IoD environment. Furthermore, the utilization of PUF holds great promise in achieving cost-effective security. PUF obviates the necessity to store confidential keys in device memory, offering a potential alternative for establishing a more secure and cost-efficient authentication framework for IoD systems. PUF empowers the SEAF-IoD to enhance its resilience against privileged insider attacks and drone/device capture attempts. To ensure the robustness of SEAF-IoD, it undergoes rigorous validation using BAN logic and Scyther simulation. Furthermore, an informal analysis affirms that SEAF-IoD fulfills critical security requirements and effectively thwarts various adversarial threats, including privileged insider, replay, and impersonation attacks. A comprehensive comparison of SEAF-IoD against existing schemes highlights its resilience and superiority in safeguarding IoD environments.

Decentralized Identity Authentication Mechanism: Integrating FIDO and Blockchain for Enhanced Security

FIDO (Fast Identity Online) is a set of network identity standards established by the FIDO Alliance. It employs a framework based on public key cryptography to facilitate multi-factor authentication (MFA) and biometric login, ensuring the robust protection of personal data associated with cloud accounts and ensuring the security of server-to-terminal device protocols during the login process. The FIDO Alliance has established three standards: FIDO Universal Second Factor (FIDO U2F), FIDO Universal Authentication Framework (FIDO UAF), and the Client to Authenticator Protocols (CTAP). The newer CTAP, also known as FIDO2, integrates passwordless login and two-factor authentication. Importantly, FIDO2’s support for major browsers enables users to authenticate their identities via FIDO2 across a broader range of platforms and devices, ushering in the era of passwordless authentication. In the FIDO2 framework, if a user’s device is stolen or compromised, then the private key may be compromised, and the public key stored on the FIDO2 server may be tampered with by attackers attempting to impersonate the user for identity authentication, posing a high risk to information security. Recognizing this, this study aims to propose a solution based on the FIDO2 framework, combined with blockchain technology and access control, called the FIDO2 blockchain architecture, to address existing security vulnerabilities in FIDO2. By leveraging the decentralized nature of the blockchain, the study addresses potential single points of failure in FIDO2 server centralized identity management systems, thereby enhancing system security and availability. Furthermore, the immutability of the blockchain ensures the integrity of public keys once securely stored on the chain, effectively reducing the risk of attackers impersonating user identities. Additionally, the study implements an access control mechanism to manage user permissions effectively, ensuring that only authorized users can access corresponding permissions and preventing unauthorized modifications and abuse. In addition to proposing practical solutions and steps, the study explains and addresses security concerns and conducts performance evaluations. Overall, this study brings higher levels of security and trustworthiness to FIDO2, providing a robust identity authentication solution.

Detecting Credit Card Fraud through Data Mining

The credit card industry grapples with a significant challenge in the form of credit card fraud, necessitating a comprehensive understanding of the various types of fraudulent activities and the evaluation of techniques deployed to detect such activities. Diverse strategies are employed by credit card firms and financial institutions, including banks, to prevent fraud, tailored to address the range of illicit behaviours encountered. The overarching goal of these efforts is to reduce instances of credit card fraud. However, persistent issues with current methodologies can lead to the erroneous classification of legitimate credit card users as fraudulent. Detecting credit card fraud through data mining entails analysing extensive datasets to identify patterns, anomalies, and trends indicative of fraudulent activities. Consequently, when employing data mining in credit card fraud detection systems, the outcome typically involves the recognition and flagging of transactions as potentially fraudulent or valid, contributing to enhanced fraud prevention measures.

Multimodal Biometric Authentication System Using of Autoencoders and Siamese Networks for Enhanced Security

Ensuring secure and reliable identity verification is crucial, and biometric authentication plays a significant role in achieving this. However, relying on a single biometric trait, unimodal authentication, may have accuracy and attack vulnerability limitations. On the other hand, multimodal authentication, which combines multiple biometric traits, can enhance accuracy and security by leveraging their complementary strengths. In the literature, different biometric modalities, such as face, voice, fingerprint, and iris, have been studied and used extensively for user authentication. Our research introduces a highly effective multimodal biometric authentication system with a deep learning approach. Our study focuses on two of the most user-friendly safety mechanisms: face and voice recognition. We employ a convolutional autoencoder for face images and an LSTM autoencoder for voice data to extract features. These features are then combined through concatenation to form a joint feature representation. A Siamese network carries out the final step of user identification. We evaluated our model’s efficiency using the OMG-Emotion and RAVDESS datasets. We achieved an accuracy of 89.79% and 95% on RAVDESS and OMG-Emotion datasets, respectively. These results are obtained using a combination of face and voice modality.

User authentication system based on human exhaled breath physics.

This work, in a pioneering approach, attempts to build a biometric system that works purely based on the fluid mechanics governing exhaled breath. We test the hypothesis that the structure of turbulence in exhaled human breath can be exploited to build biometric algorithms. This work relies on the idea that the extrathoracic airway is unique for every individual, making the exhaled breath a biomarker. Methods including classical multi-dimensional hypothesis testing approach and machine learning models are employed in building user authentication algorithms, namely user confirmation and user identification. A user confirmation algorithm tries to verify whether a user is the person they claim to be. A user identification algorithm tries to identify a user's identity with no prior information available. A dataset of exhaled breath time series samples from 94 human subjects was used to evaluate the performance of these algorithms. The user confirmation algorithms performed exceedingly well for the given dataset with over 97% true confirmation rate. The machine learning based algorithm achieved a good true confirmation rate, reiterating our understanding of why machine learning based algorithms typically outperform classical hypothesis test based algorithms. The user identification algorithm performs reasonably well with the provided dataset with over 50% of the users identified as being within two possible suspects. We show surprisingly unique turbulent signatures in the exhaled breath that have not been discovered before. In addition to discussions on a novel biometric system, we make arguments to utilise this idea as a tool to gain insights into the morphometric variation of extrathoracic airway across individuals. Such tools are expected to have future potential in the area of personalised medicines.

Lightweight blockchain-based remote user authentication for fog-enabled IoT deployment

The Internet of Things (IoT) seeks to enhance human life by embedding everyday objects with intelligence. As deployed in diverse environments, IoT devices exchange substantial data to offer autonomously smart and innovative services. Cloud computing serves as an effective solution for processing and storing data from IoT devices, enabling remote access for end-users. However, authenticating remote users poses a critical challenge. Although several existing schemes tackle this challenge, they have notable security and performance weaknesses. This paper introduces a lightweight, distributed multi-factor authentication scheme for remote users in IoT. The proposed approach, named Lightchain, integrates blockchain technology and fog computing while incorporating a lightweight cryptographic hash function. The security of Lightchain is rigorously confirmed through formal verification using the well-recognized Automated Validation of Internet Security Protocols and Applications (AVISPA) tool. Additionally, we develop and assess Lightchain’s functionality using the solidity language across diverse use cases. A comparative analysis is presented to evaluate performance costs and security requirements against recent methods. The proposed scheme demonstrates efficiency and robustness, making it well-suited for a range of IoT applications.