Differentially Private Clustering with Dynamic Noise Adjustment (DPC-DNA) based Fusion Anonymity and Privacy Enhancement in Big Data

Sergey

doi:https://doi.org/10.54216/NIF.040105

Journal of Cybersecurity and Information Management | 2025

Detecting Zero-day Polymorphic Worms Using Honeywall

A polymorphic worm is a kind of worm that can change its payload in every infection attempt, so it can evade the Intrusion Detection Systems (IDSs) and perform illegal activities that lead to high losses. These worms can mutate as they spread across the network, causing most of the existing IDSs to carry out the polymorphic worm’s detection with high levels of both false positives and false negatives. In this paper, we propose a double-honeynet system that can detect polymorphic worm instances automatically. The Double-honeynet system is a hybrid system with both Network-based and Host-based mechanisms. This allows us to collect polymorphic worm instances at the network-level and host-level, which reduces the false positives and false negatives dramatically. The experimental deployment of a Double-honeynet network over a seven-day period successfully collected instances of various polymorphic worms, including 3511 Allaple, 3228 Conficker, 2817 Blaster, and 2452 Sasser worms. By utilizing, the Honeywall's Walleye interface; we were able to analyze the data and simulate the detection of these worms by generating new signatures, which were not previously recorded, demonstrating the system's capability to detect zero-day polymorphic threats. Analysis of Blaster worm instances revealed significant similarities in their payloads due to exe headers, indicating the necessity of preprocessing to remove these headers before signature generation, although the generation of signatures is beyond the scope of this study.

groups

Mohssen Mohammed mail -

Mohamed Abdalla Nour mail -

Mohamed Elhoseny mail

link https://doi.org/10.54216/JCIM.150104

Volume & Issue

Vol. Volume 15 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2024

Fusion of Artificial Intelligence Based Deep Learning Model for Product Reviews on E-Commerce Environment

The emergence of e-commerce is introduced in the golden era. E-commerce product reviews are comments generated by customers of online shopping to estimate the service and product qualities having purchased; these remarks aid users in identifying the facts of the product. The sentiment polarity of e-commerce product analyses is the optimal method to get consumer opinions on a service or product. Hence, sentiment analysis (SA) of product remarks on e-commerce platforms is much more influential.  Deep learning (DL) analysis of online consumer feedback can identify user behavior toward a sustainable future. Artificial intelligence (AI) can acquire perceptions from product evaluations to develop efficient products. The main challenge is that numerous ethical products do not satisfy customers’ expectations owing to the gap among users’ expectations and their perception of sustainable products. This paper focuses on the design of the Fusion of Artificial Intelligence Deep Learning Model for Product Reviews on E-Commerce (FAIDLM-PREC) model. The main intention of FAIDLM-PREC method is to appropriately distinguish the dissimilar types of sentiments that occur in the e-commerce reviews.  Initially, data preprocessing is executed to increase the product review quality with Glove based word embedding method. For product reviews classification, the FAIDLM-PREC approach evolves fusion of dual DL methods namely Bidirectional Long Short‐Term Memory (Bi-LSTM) and gated recurrent unit (GRU) methods. Eventually, the parameters relevant to the two DL methods are perfectly modified utilizing the Archimedes optimization algorithm (AOA). An extensive experiment of the FAIDLM-PREC technique was conducted utilizing customer review database and outcomes indicated that the FAIDLM-PREC technique highlighted betterment over other recent methods to several measures.

groups

Nasser Nammas Albogami mail

link https://doi.org/10.54216/FPA.160212

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

Pure Mathematics for Theoretical Computer Science | 2024

On the Assessment Restricted Liu Estimator for Dealing with Multi-Collinearity Problem

In this paper, we concentrate on comparing the restricted least squares with restricted Liu estimator  based on (MSE) criterion in the existence of multi-collinearity. In addition, we find the best estimation in many different cases with some related numerical examples.

groups

Noor Edin Rabeh mail

link https://doi.org/10.54216/PMTCS.040105

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

A Plithogenic Statistical Approach to Assessing the Effects of Ginger Powder as a Growth Promoter

In a world where efficiency and sustainability in poultry production are crucial, the need arises to find natural additives that enhance the growth of broiler chickens  ̣Recent research has put ginger powder under the microscope, evaluating its impact as a growth promoter through a detailed analysis of plithogenic statistics  ̣This study not only focuses on the quantitative aspects of weight gain and improved feed conversion, but also on the qualitative effects that this additive may have on the general health and well-being of the birds  ̣ The methodology used involves a rigorous and multifaceted approach, integrating biological and nutritional variables, which allows a deep and holistic understanding of the benefits of ginger powder in poultry farming  ̣Preliminary results suggest that ginger powder could be a viable alternative to synthetic growth promoters, showing significant improvement in growth parameters of broilers  ̣ However, plithogenic analysis reveals complex nuances that require careful interpretation, as variations in bird response indicate that factors such as dosage and administration time are crucial to maximizing benefits  ̣ This finding opens a range of possibilities for future research and practical applications, pointing towards more natural and sustainable poultry production  ̣ Additionally, it raises important questions about the integration of herbal supplements into animal diets, inviting a broader debate about science and ethics in the food industry. 

groups

Lucía Monserrath Silva Déley mail -

Dorian Michael Lisintuña Montaguano mail -

Jaime Iván Acosta Velarde mail -

Blanca Mercedes Toro Molina mail -

Blanca Jeaneth Villavicencio Villavicencio mail -

Edilberto Chacón Marcheco mail

link https://doi.org/10.54216/IJNS.250144

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Finding new similarities measures for Type-II Diophantine neutrosophic interval valued soft sets and its basic operations

The Type-II Diophantine neutrosophic interval valued soft set (Type-II DioNSIVSS) and related similarity measure are presented in this study. An extension of the neutrosophic interval valued soft set (NSIVSS) and the Diophantine fuzzy soft set is the Type-II DioNSIVSS. The suggested measure for Type-II DioNSIVSS assessment. We support a method of solving the problem using the Type-II soft set model. To demonstrate how they can be applied to successfully handle uncertainty-related challenges, illustrative examples are given.

groups

Sharifah Sakinah Syed ahmad mail -

Nasreen Kausar mail -

Murugan Palanikumar mail

link https://doi.org/10.54216/IJNS.250145

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

A Hybrid Intelligence-based Deep Learning Model with Reptile Search Algorithm for Effective Channel Estimation in massive MIMO Communication Systems

Channel estimation poses critical challenges in millimeter-wave (mmWave) massive Multiple Input, Multiple Output (MIMO) communication models, particularly when dealing with a substantial number of antennas. Deep learning techniques have shown remarkable advancements in improving channel estimation accuracy and minimizing computational difficulty in 5G as well as the future generation of communications. The main intention of the suggested method is to use an optimal hybrid deep learning strategy to create a better channel estimation model. The proposed method, referred to as optimized D-LSTM, combines the power of a deep neural network (DNN) and long short-term memory (LSTM), and the optimization process involves the integration of the Reptile Search Algorithm (RSA) to enhance the performance of  deep learning model. The suggested hybrid deep learning method considers the correlation between the measurement matrix and the signal vectors that were received as input to predict the amplitude of the beam space channel. The newly proposed estimation model demonstrates remarkable superiority over traditional models in both Normalized Mean-Squared Error (NMSE) reduction and enhanced spectral efficiency. The spectral efficiency of the designed RSA-D-LSTM is 68.62%, 62.26%, 30.3%, and 19.77% higher than DOA, DHOA, HHO, and RSA. Therefore, the suggested system provides better channel estimation to improve its efficiency.

groups

Nallamothu Suneetha mail -

Penke Satyanarayana mail

link https://doi.org/10.54216/JISIoT.130227

Volume & Issue

Vol. Volume 13 / Iss. Issue 2

Details open_in_new

Neutrosophic and Information Fusion | 2024

The basis number of connected vertex-disjoint graphs

The basis number b (G) of a graph G is defined to be the smallest positive integer k such that G has a k-fold basis for its cycle space. We try to find an upper bound for b (G_1+G_2+G_3+G_4). We prove that, if G_1,G_2,G_3 and G_4 are connected vertex-disjoint graphs and each has a spanning tree of vertex degree not more than 4, then b(G_1+G_2+G_3+G_4)≤max{4,b(G_1)+1,b(G_2)+2,b(G_3) +2,b (G_4)+1}. The basis number of quadruple join of paths will be studied, where we prove that b p_m+ p_n+p_p+p_t) =4, ∀m,t≥5  and n,p≥6.

groups

Barbara Charchekhandra mail

link https://doi.org/10.54216/NIF.040101

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Neutrosophic and Information Fusion | 2024

On the Computation of Units in Symbolic 4- Plithogenic Ring of Integers

In this paper, we study the invertible elements (units) in the symbolic 4-plithogenic ring of integers, where we use a computational algorithm to find all units in the mentioned ring. The all-elements group of 32 symbolic 4-plithogenic ring of integers has been found and listed.

groups

Lee Xu mail

link https://doi.org/10.54216/NIF.040102

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Neutrosophic and Information Fusion | 2024

Design and Implementation of Fuzzy Logic-Based Key Exchange Protocol in Medical Image Cryptographic Protection Scheme

Images may be protected from hackers and attackers with the use of steganography. The rapid expansion of the internet has led to the widespread distribution of vast quantities of multimedia content, including photos, movies, and audio files, via various online platforms. To ensure the safety of sensitive information while it is in transit and upon receipt, a high degree of security is required. During the patient scanning procedure, hospitals and scan centers save many pictures of patients on personal computers. Protection from strangers who may see the patients' scanned photos would be necessary for this. Therefore, scan centers and hospitals all over the globe rely heavily on medical image security. The proposed technique includes Fuzzy Logic-Based Key Exchange Protocol in Medical Image Cryptographic Protection Scheme.  To provide the utmost protection for the medical pictures, the cover image incorporates the secret image. At the outset, we standardize the cover and hidden photos. The cover image for this thesis might be a picture of nature or a benchmark; the hidden image, on the other hand, is a medical image in grayscale or binary format. After that, the normalized picture is processed using DWT. The hidden picture is embedded into the cover image using a fuzzy-based edge-related steganography approach, which uses these altered coefficients. To get the stego image, the embedded picture is normalized in the reverse direction. Additionally, this study suggests DT-CWT transform based picture security. Part one of the suggested approach to picture security is image steganography, and part two is picture cryptography. Module 1 uses the DT-CWT transform to fuse the coefficients of the cover picture with the hidden image. After that, the steganography picture is subjected to module 2, which is based on the IE calculation. Analysis of experimental data for the suggested picture security approach revealed improved outcomes for encrypted communication.

groups

Erina Kovachiskaya mail

link https://doi.org/10.54216/NIF.040104

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Neutrosophic and Information Fusion | 2024

Differentially Private Clustering with Dynamic Noise Adjustment (DPC-DNA) based Fusion Anonymity and Privacy Enhancement in Big Data

Other few challenges faced during privacy preservation by anonymity e.g. difficulty in identifying the The main challenges in preserving anonymity for privacy are determining which attributes could undermine privacy and extracting useful information from massive databases without disclosing sensitive details. We developed a Novel Framework for Differentially Private Clustering with Dynamic Noise Adjustment (DPC-DNA) that addresses these issues. This novel approach can recognize sensitive and non-sensitive data aspects using Differentially Private Clustering with Dynamic Noise Adjustment (DPC-DNA). The accuracy of clusters formed by DPC-DNA was assessed using the silhouette score, which gauges how similar each item is to its own group versus others. DPC-DNA achieved a silhouette score of 0.62, signalling strong internal cluster composition. In contrast, traditional k-anonymity clustering yielded a lower score of 0.45, confirming that DPC-DNA significantly boosts accuracy. Our Novel Framework for Differentially Private Clustering with Dynamic Noise Adjustment (DPC-DNA) provides a robust solution for privacy-preserving data mining. By combining differential privacy with adaptive noise management, it safeguards sensitive material while sustaining high precision, integrity and usefulness of results.

groups

Sergey Drominko mail

link https://doi.org/10.54216/NIF.040105

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new