SMART DOCUMENT PROTECTION SYSTEM WITH DUAL BIOMETRIC AUTHENTICATION AND SECURITY ALERTS

 Internet of Things (IoT)-enabled intelligent systems are proliferating rapidly, providing the capability to connect virtually any device to the Internet. Consequently, this concept can be effectively utilized in home security applications. In this paper, we have introduced an IoT-enabled system designed to send security alerts to users via email upon detecting human intrusion. The system comprises a PIR sensor, Pi camera, Raspberry Pi-3, and an Internet connection. There are two operational modes in the proposed security system. In the first mode, movement by an intruder is detected, and simultaneously, every time someone rings the doorbell, the Pi camera captures an image. The system then accesses a stored database to ascertain whether the individual is recognized. If the person is unfamiliar, the user receives an email notification, including the captured image of the individual. On the other hand, if the person is recognized, the system stores the captured image. In the second mode, when someone exhibits suspicious behaviour in front of the door, the system sends an alert email to the user, prompting them to activate the security alert system installed at the entrance. For face detection, we employ the Haar cascade technique. Face recognition involves two steps: feature extraction and classification. In the feature extraction phase, we compare various algorithms, and a comparative study of these provides a methodology that achieves 99.56% accuracy, outperforming other existing models. The developed system leverages the IoT platform to fortify security against intruders, thereby fostering a safe and secure environment.

The rapid expansion of Internet of Things (IoT) quickly evolves towards a connected network of AI-enabled, smart, multi-sensory devices that generate, consume and exchange enormous amounts of data. Stimulated by the omnipresent cloud-services and ever widening data bandwidth they aspire to control every aspect of our lives from transportation to our health, significantly increasing our reliance on the web-based services and their security. Already millions of cyber security alerts are generated every day and trigger increasingly costly investigations of the Security Operations Centres (SOC). In order to make their operation more efficient security warnings need to be reliably detected and classified based on various levels of severity, scale of potential damage or an ability to defend. We have responded to this challenge in the context of IEEE BigData Cup 2019 focused on predicting cyber security threats that require attention based on detailed logs of network activity leading to the security alert. We have developed a hybrid supervised learning ensemble model combining several state-of-the-art Extreme Gradient Boosting algorithms. Specifically, xGBoost and LightGBM model versions have been built on separate sets of features extracted from the raw logs of network events preceding the alerts and then synergically aggregated. Models' diversity imposed by algorithmic differences, complementary feature subsets, and individually optimized hyperparameters, combined with robust stratified cross-validation scheme resulted with the best true alerts detection rate yielding the AUC score in excess of 0.93, that outperformed all other 248 competing teams.

Correlating and analyzing security alerts is a critical and challenging task in security management. Recently, some techniques have been proposed for security alert correlation. However, these approaches focus more on basic or low-level alert correlation. In this paper, we study how to conduct probabilistic inference to correlate and analyze attack scenarios. Specifically, we propose an approach to solving the following problems: 1) How to correlate isolated attack scenarios resulted from low-level alert correlation? 2) How to identify attacker's high-level strategies and intentions? 3) How to predict the potential attacks based on observed attack activities? We evaluate our approaches using DARPA's grand challenge problem (GCP) data set. The results demonstrate the capability of our approach in correlating isolated attack scenarios, identifying attack strategies and predicting future attacks.

Abandoned object detection is used to identify the unattended, strange object for a specific time period. Abandoned object detection plays a vital role in the places where there is high security alerts e.g. terrorist hits. Human feature Detection is done to differentiate between humans from arbitrary objects. It is implemented for the real time situation and capturing of live streaming videos. In previous methodologies only security alarms were used to alert the user. But proposed system checks whether the detected abandoned object is human being or static object like bag. The image of abandoned object is sent to the security guard through E-Mail and Android Application. This system is divided into three parts as follows: 1. Abandoned Object Detection 2. Human feature Detection 3. Security Alert System.

Using passwords remains the most common way to authenticate users for various types of information systems. This poses the challenge of securing the storage of user authentication information and protecting it from unauthorized access. In practice, various algorithms for secure password storage have become widespread. Mutually contradictory requirements for such algorithms for secure password storage, which on the one hand must be complex enough to coun ter various attacks, and on the other – simple to ensure the speed of the information system – determine the relevance of the study. There is a significant threat of direct search, especially given the fact that the computing power of CPUs and GPUs is constantly growing. Therefore, there is a need to be able to change the complexity of the hash code calcula tion, and therefore the amount of computation and time so as to significantly complicate the attack, but not cause dis comfort to the end user due to the delay in password verification. Among the known methods of secure password stor age are password encryption, the use of the hash function in the classical version, as well as the addition of salt and the use of iterations to calculate the hash code. The comparative analysis of the given methods is carried out in the work, their advantages and disadvantages are established, expedient areas of application of each method are outlined, the corresponding recommendations are developed. For the computational experiment, the tools of the Microsoft .NET Core 3.1 platform were used, which made it possible to set the time indicators of the hash code generation algorithm depending on the set parameters of the algorithm. The data obtained from the experiment can be used to select a method of securely storing passwords.

The Smart Anti-Theft Car System is an innovative project designed to enhance the security features of conventional vehicles and mitigate the risks associated with unauthorized access and theft. In response to the growing challenges of automotive theft, this project introduces a comprehensive and intelligent anti-theft system integrated with cutting-edge technologies. The primary focus is leveraging IoT (Internet of Things) and real-time connectivity to create a robust security framework. The project incorporates various features to provide an advanced and proactive defense against car theft. Key components include GPS tracking, biometric authentication, and smart sensors, all seamlessly integrated into a centralized control system. The system detects suspicious activities and employs preventive measures to thwart theft attempts. In this project, a user-friendly mobile application serves as a central interface, allowing car owners to monitor and control the security status of their vehicles remotely. Real-time alerts and notifications provide instant updates on security breaches, enabling swift response actions. The integration of IoT enables the collection and analysis of data, contributing to the continuous improvement of the system's effectiveness. The Smart Anti-Theft Car System project represents a significant step forward in automotive security, aligning with the contemporary shift towards smart and connected vehicles. The implementation of this system aims to offer car owners peace of mind by providing a proactive, intelligent, and user-centric approach to preventing car theft. This project contributes to the evolving landscape of smart and secure transportation systems by integrating modern technologies

In today’s digital landscape, where data is a critical asset for businesses, building a resilient backup infrastructure is paramount to ensuring data availability and protection. This research investigates the synergy between three essential elements—data redundancy, encryption, and Role-Based Access Control (RBAC) to enhance backup system resilience. Data redundancy, achieved through methods like the 3-2-1 rule and cloud replication, ensures continuous availability and protection against hardware failures. Encryption secures backup data, making it unreadable to unauthorized users and safeguarding sensitive information in compliance with regulatory standards. RBAC, on the other hand, provides granular control over user access, enforcing the principle of least privilege and minimizing the risk of unauthorized data manipulation. By combining these strategies, organizations can mitigate the risks of data loss, breaches, and unauthorized access, creating a robust, secure, and efficient backup infrastructure. This paper provides a comprehensive analysis of how these technologies can be integrated, offers best practices for implementation, and discusses the future of backup systems in an increasingly complex threat environment. Keywords: Backup Infrastructure, Data Redundancy, Data Encryption, Role-Based Access Control, RBAC, Data Security, Disaster Recovery, Data Protection, Cloud Backup, Data Availability, Security Best Practices, IT Resilience, Cybersecurity, Backup Strategies.

Network security encompasses the strategies and techniques to protect networks from unauthorized access and potential threats. Network security is essential to protect layers of networks and data transferring on them. Data integrity and the underlying network infrastructure are necessary in today’s digital landscape. This paper explores the role of machine learning (ML) in enhancing network security by developing intelligent tools and methodologies. We critically analyze various ML techniques utilized in this field, their practical applications, and the advancements achieved in fortifying networks against cyber threats. We address ML’s challenges and limitations in network security, concluding with a discussion of open research issues for future investigation.

This paper explores a comprehensive, multi-layered approach to securing cloud infrastructures, emphasizing the critical importance of data protection in today’s digital landscape. As organizations increasingly migrate to the cloud, they face heightened risks of data breaches and cyber threats. Our proposed framework integrates various security measures, including encryption, access control, intrusion detection systems, and continuous monitoring, to create a robust defense against unauthorized access and data loss. We discuss the effectiveness of each layer in mitigating vulnerabilities and ensuring compliance with regulatory standards. Additionally, the paper highlights best practices for implementing these strategies, tailored to different organizational needs. By adopting this multi-layered approach, businesses can enhance their overall security posture, safeguard sensitive information, and maintain customer trust in cloud-based services.

Web applications are widely used in today's digital landscape, necessitating robust security measures to protect against unauthorized access by malicious users. Ensuring the security of these applications requires effectively identifying and addressing vulnerabilities. This paper proposes an automated methodology for vulnerability detection, utilizing a genetic algorithm to generate test cases, which offers greater efficiency and performance compared to resource-intensive and time-consuming manual approaches. Our research highlights the effectiveness of genetic algorithms as test data generators, leveraging insights from previous studies. Given the varying severity of Structured Query Language (SQL) injection attacks, those capable of executing destructive commands, such as the "drop" command, pose a more significant threat than those that merely disclose information. We employ both white-box and black-box testing methodologies to detect SQL injection vulnerabilities. Black box testing is utilized when the source code is unavailable, while white box testing is applied when the source code is accessible. Our findings suggest that white box testing, particularly static analysis, is more effective in identifying vulnerabilities. This study aims to enhance web application security by utilizing genetic algorithms to generate optimal test cases for vulnerability detection, providing a comprehensive approach that integrates white-box and black-box testing.

Privacy-Preserving Fuzzy Commitment Schemes (PPFCS) have emerged as a promising solution for secure Internet of Things (IoT) device authentication, addressing the critical need for privacy and security in the rapidly growing IoT ecosystem. This paper presents a novel PPFCS-based authentication mechanism that protects sensitive user data and ensures secure communication between IoT devices. The proposed scheme leverages error-correcting codes (ECC) and cryptographic hash functions to achieve reliable and efficient authentication. The PPFCS framework allows IoT devices to authenticate themselves without revealing their true identity, preventing unauthorized access and preserving users’ privacy. Furthermore, our PPFCS-based authentication mechanism is resilient against various attacks, such as replay, man-in-the-middle, and brute-force attacks, by incorporating secure random nonce generation and timely key updates. We provide extensive experimental results and comparative analysis, demonstrating that the proposed PPFCS significantly outperforms existing authentication schemes in terms of security, privacy, and computational efficiency. As a result, the PPFCS offers a viable and effective solution for ensuring secure and privacy-preserving IoT device authentication, mitigating the risks associated with unauthorized access and potential data breaches in the IoT ecosystem.

Nowadays, to provide a picture of the current intrusive activities in the network, detection methods are important to tackle the probable risks of attackers' malicious behaviors. Intrusion Detection Systems (IDSs), as detection solutions, are one of the main devices to record and analyze suspicious activities. A huge number of low-level alerts generated by IDSs clearly reflect the need for a novel alert correlation system to reduce alert redundancy, correlate security alerts, and discover multi-step attack scenarios. In this paper, we propose a novel alert correlation framework which processes the generated alerts in real time, correlate the alerts, construct the attack scenarios using the concept of Bayesian networks and forecasts the next goal of attackers using the creation of attack prediction rules. The proposed framework has two modes: on-line and offline. In the off-line mode, a Bayesian Attack Graph (BAG) is constructed using the concept of Bayesian networks. Then, in the on-line mode, the most probable next steps of the attacker are predicted. Experimental results show that the framework is efficient enough in detecting multi-step attack strategies without using any predefined knowledge. The results also show that the algorithm perfectly forecasts multi-step attacks before they can compromise the network.

As cyber threats continue to evolve in complexity and frequency, conventional intrusion detection systems (IDS) often fail to detect advanced and novel attacks. This project introduces an intelligent Network Intrusion Detection System (NIDS) leveraging Deep Learning to efficiently identify and categorize network intrusions. It analyzes live network traffic and determines whether it is legitimate or malicious using advanced machine learning models. Prior to training, the dataset undergoes preprocessing with techniques like One-Hot Encoding and Min-Max Scaling to enhance model performance. The final model is integrated into a Flask-based web application that provides real-time monitoring and alerts for suspicious activity. Unlike traditional IDS that rely on predefined signatures, this solution is capable of identifying zero-day threats by recognizing behavioral patterns in historical data. By evaluating and comparing different deep learning architectures, the system strives for superior detection metrics such as accuracy, precision, and recall. Ultimately, this approach aims to strengthen organizational cybersecurity and minimize the risk of data breaches and unauthorized access. Key Words: Network Intrusion Detection System (NIDS), Intrusion Detection System (IDS), Deep Learning,Cybersecurity

Image encryption is an indispensable technique in the realm of information security, serving as a pivotal mechanism to safeguard visual data against unauthorized access and potential breaches. This study scrutinizes the effectiveness of merging columnar transposition with the Hill Cipher methodologies, unveiling specific metrics from a curated set of sample images. Notably, employing column transposition with the key "JAYA" and the Hill Cipher with the key "UDINUSSMG," the encrypted images underwent rigorous evaluation. 'Lena.png' demonstrated an MSE of 513.32 with a PSNR of 7.89 dB, while 'Peppers.png' and 'Baboon.png' recorded MSE values of 466.67 and 423.92, respectively, with corresponding PSNR figures of 7.12 dB and 7.31 dB. Across all samples, a consistent BER of 50.00% indicated uniform error propagation, while entropy values settled uniformly at 7.9999, highlighting consistent data complexity. While the findings underscore a consistent error rate and complexity, there's a compelling need for further refinement to enhance image quality and security. Moreover, the study proposes future research avenues exploring a three-layer super encryption paradigm, amalgamating columnar transposition, Hill Cipher, and other robust algorithms. This approach aims to fortify encryption methodologies against evolving threats and challenges in data protection, offering heightened resilience and efficacy in safeguarding sensitive information.

Healthcare data security solutions are needed that will be able to withstand the growth of cloud computing in storing and sharing healthcare records. With traditional authentication mechanisms such as passwords and single-modal biometrics, cyber threats and unauthorized access are a reality. The study provides a biometric security system for the cloud by using artificial intelligence that integrates deep learning for anomaly detection and homomorphic encryption with multimodal biometrics, such as voice authentication, face recognition, and fingerprints. In this proposed system, the maintenance of compliance with such regulatory requirements as GDPR and HIPAA guarantees safe and easy access to healthcare data. With the instant detection of suspicious access patterns, AI-driven anomaly detection enhances security, and blockchain technology ensures immutable recording for auditability. Edge computing further optimizes the authentication response time for efficient system operation. Results demonstrate the system with high authentication accuracy, quick reaction time, and robust resistance to cyber-attacks. This solution is based on addressing the important need of better security for current healthcare systems, thus providing safe, scalable, and privacy-preserving healthcare data exchange.