Journal of Web Development and Web Designing

Three-Way Authentication for Transaction Using Cloud Computing

Anjali Chillal, Jyoti Patil, Kiran Shendge, Ashwini Hiremath, K. M. Tamboli — Tue, 31 Oct 2023 00:00:00 +0530

The main objective of this research is to employ the Three Factor Authentication approach to make cloud computing more secure. A foolish assumption to carry out, we will most likely make use of a standard ABS. Furthermore, just divide the client's secret key into two halves. While one portion is stored on the client's PC, another is integrated into the security device. Since the attacker may have traded off one of the elements in three 3FA and regular ABS does not guarantee that the spilling of part of the secret key does not damage the security of the plan, extraordinary thought must be given to the process. Furthermore, since the security device shouldn't be able to handle the bulk of the computation, the component should be completed in a way that places the majority of the weight on the client's PC. Even though the new method of cloud computing offers many benefits, there are still some issues with security and authentication, particularly for web-based cloud computing services. As sensitive data may be stored in the cloud for convenience or security reasons, and as eligible users may also access the cloud for a variety of applications and services, user authentication poses a significant challenge for any cloud system. With the help of the One Time Password (OTP) & the Lightweight Security Device, both of which are used for user authentication, the proposed three fine-grained (3FA) approaches provide the cloud with more security. As a result, this system resolves the user authentication issue, which is a major challenge for the cloud system. As a user or authority uploads a file to the cloud, that file is divided into several blocks, increasing security. This prevents any hacker from being able to access the entire file. It has been demonstrated that the suggested 3FA access control solution maintains client security while allowing control over the cloud server and limiting access to customers with comparable property plans. An in-depth analysis of security reveals that the proposed 3FA get-to-control structure covers all security requirements.

Keep Your Digital Life Safe

Tue, 26 Dec 2023 00:00:00 +0530

In today’s world mobile is a must thing to have for everyone because of its numerous uses and advantages. Along with advantages, there are many issues for almost lakhs of people that are hacking and cybercrime has been increased. In the current world, we have 5.48 billion mobiles getting hacked every day and at least 2200 mobile get hacked every day which is around 800000 users hacked every year. There are many ways to hack a mobile but the main and easy type of mobile hacking is “phishing”. To overcome this hacking, we have developed an app named lookout security which will secure the mobile data of mobile users.

ANN-Based Dengue Prediction Model

Wed, 20 Dec 2023 00:00:00 +0530

Dengue fever is a substantial global health challenge, demanding early and accurate diagnosis for effective patient care. This paper presents a robust Artificial Neural Network (ANN) approach implemented in the Colab Notebook for Dengue diagnosis. The study's methodology, dataset, implementation details, and results are outlined. The ANN model's superior diagnostic performance compared to traditional methods demonstrates its potential to revolutionize Dengue diagnosis. Dengue fever is a significant global health concern, with millions of cases reported each year. Early and accurate diagnosis is crucial for effective patient management and disease control. This abstract presents a novel approach for dengue diagnosis using Artificial Neural Networks (ANN). Traditional diagnostic methods, such as serological tests and PCR assays, have limitations in terms of cost, time, and accuracy. ANN offers an alternative solution by leveraging its ability to process complex data patterns and make predictions based on a variety of input variables. In this study, we collected clinical, haematological, and demographic data from a cohort of dengue patients and used them as input features for the ANN. The proposed ANN model is trained using a large dataset of dengue cases, which includes various stages of the disease. The neural network is designed to learn and recognize subtle patterns accurately. The ANN's architecture and hyperparameters are optimized to achieve high diagnostic accuracy accurately. The ANN's architecture and hyperparameters are optimized to achieve high diagnostic accuracy. Severe dengue can be life-threatening and requires prompt medical attention. ANNs can potentially address the limitations of existing diagnostic methods by providing more accurate, efficient, and timely diagnoses.

Reinforcement Learning and Decision Making

Bhuvaneshwari. S, S. Nirmala Sugirtha Rajini — Fri, 29 Dec 2023 00:00:00 +0530

The study of reinforcement learning is a machine learning paradigm in which agents learn to make decisions by interacting with an environment and obtaining rewards for their actions. Agents use trial and error to find optimal rules that maximize cumulative rewards over time. This strategy is well-suited for complex, dynamic contexts where traditional methods may fall short. Key issues include balancing exploration and exploitation, dealing with delayed rewards, and managing huge state and action spaces. Deep reinforcement learning, which blends deep neural networks with reinforcement learning, has shown exceptional success in a variety of applications, demonstrating the potential for intelligent decision-making in a variety of fields. Ongoing research continues to develop algorithms and extend the possibilities of reinforcement learning for future real-world applications.

Generative Artificial Intelligence (AI)

Asha S.Kabadi, Manasa S. Bagashetti, Aishwaraya S.Navi — Fri, 29 Dec 2023 00:00:00 +0530

Large advanced AI systems (like LGAIMs such as ChatGPT, GPT-4, OR stable diffusion) are quickly changing how we talk, depict, and produce content. Yet, regulations for AI, both in the EU and globally, have mainly targeted tadeonal AI models, overlooking LGAIMs. This paper seeks to place the new generative models in the appropriate context within the ongoing discussions about trustworthy AI regulations. It will investigate how the legal framework can be customized to accommodate their capabilities the subsequent legal section from the document will be organized into four steps, addressing direct regulation, data protection, moderated content, and proposing policies. The text proposes a fresh approach to define the artificial intelligence value containing the LGAIM (Large Generalized AI Models) context, distinguishing between LGAIM outputs. The regulatory responsibilities are customized for various entities across the value chain, ensuring the trustworthiness and societal benefits of LGAIMs. The paper advocates across the three tiers of obligations: baseline criteria applicable to every LGAIM, high responsibilities risk for specific use cases, and collaborative efforts throughout the AI value chain. Additionally, the regulation outlined within the AI legislation and additional explicit regulations must align with the unique characteristics inherent within a retrained model. In a broader sense, the emphasis of regulation should be on specific high-applications rather than the pre-trained model itself. Such regulations should encompass transparency and risk management obligations. However, non-discrimination provisions might apply finally to developers of Large-Scale Generative AI Models the core Guidelines for moderating the content of the DSAs should be clarified to include LGAIMs, which involve notification and response mechanisms along with trusted flaggers.