Authors - Deepak sharma, Pankajkumar Anawade, Anurag Luharia, Gaurav Mishra Abstract - The rapid digital transformation of modern society has significantly increased the complexity of network infrastructures and the sophistication of cyber threats. Traditional rule-based and signature-based security systems are increasingly ineffective against advanced persistent threats, zero-day vulnera bilities, and AI-driven cyberattacks. Artificial Intelligence (AI) and Machine Learning (ML) have emerged as transformative technologies that enhance net work security through intelligent threat detection, automated response, and pre dictive analytics. However, the integration of AI and ML also introduces new vulnerabilities, including adversarial attacks, model poisoning, privacy con cerns, and algorithmic bias. This paper critically examines the evolution of net work security through AI and ML, analyzing both the technological advance ments and the emerging risks associated with their deployment. The study ar gues that while AI-driven security systems represent a significant improvement over traditional mechanisms, careful governance, transparency, and robust model protection are essential to mitigate new threats introduced by intelligent systems.
Authors - Isha Bhagat, Rishita Chourey, Anjali Kurhade, Vedika Desai, Meenal Kamalakar, Vishal Goswami, Nayan Wagh Abstract - In the shadow of overlooked safety violations, different factories have lost thousands, in terms of capital as well as lives. Which is especially harrowing as these were caused due to easily preventable work accidents or easily noticeable defective machinery. Our paper dives into how artificial intelligence based methodologies, particularly, would help in mitigating these risks based on past and present research. We also recommend a potential prototype system according to the findings from the literature we reviewed, for Real-Time worker safety check and automated industrial machine quality inspection system. We have reviewed four major topics pertaining to our system: [1] Personal Protective Equipment (PPE) compliance detection through CCTV monitoring as opposed to manual monitoring, [2] industrial machine quality inspection for automatic defect identification [3] evaluation of previously used object detection models and their performance for industry applications, and [4] system level considerations for practical deployment of the said systems on a large scale. We have compared methods, deployment strategies and results from existing studies to identify key criteria like scalable architectures as well as low latency processing. We are highlighting challenges such as insufficient annotated data for rare machinery defects, good accuracy in harsh industrial conditions that might hinder detection of safety violations, and ethical issues with worker monitoring as well in this paper.
Authors - P Subhash, P. Abhi Varshini, V. Udai Sree, P. Praneeth Reddy, Sai Mahitha Abstract - The recognition of transaction fraud in credit cards is a major problem that is still faced. It is mainly because of the gap between real and fraud transaction. In traditional methods, evaluations are mainly done with the main eye on accuracy, but it is sometimes inadequate and indecisive because the fraud occurrence is only 1% of all the data. Many studies in this field that have been done lately have focused on deep learning and machine learning structures. A very less number of works really stress on relatively simpler structures that can go well with imbalance and variance in class without the need of any complicated frameworks. A dataset that is publicly accessible has been used here for comparative study and has 284,807 transaction data. For classification, three learning algorithms like Logistic Regression, Random Forest, and XGBoost have been used. Precision-Recall AUC (PR-AUC), Matthews Correlation Coefficient (MCC), precision, and recall have been used to assess the model performance and not just accuracy. Random forest shows a steady outcome with a strong variance between false positive control and detection capability. The analysis also reveals that naive class-weighting strategies can significantly increase recall while producing impractically high false positive rates. Feature importance analysis further enhances interpretability and provides insight into influential transaction components.
Authors - Tintu Pious, Adon Hale J Payyapilly, Akshit Charan, Amal Suresh, Ashwin Babu Mampilly Abstract - The shift toward decentralized energy grids has established Vehicle-to-Vehicle (V2V) power transfer as a cornerstone of modern EV infrastructure. Central to this exchange is the Dual Active Bridge (DAB) converter, a bidirectional DC-DC topology prized for its high power density and galvanic isolation. The DAB utilizes two symmetrical H-bridges linked by a high-frequency transformer; one bridge acts as an inverter while the other performs synchronous rectification, depending on the power flow direction. Managing energy between independent batteries is challenging due to fluctuating voltage levels that create "moving targets" for control systems. Traditional PID loops often struggle with the instability caused by sudden voltage shifts in dynamic V2V scenarios. This project implements a Fuzzy Logic Controller (FLC) based on a voltage mapping principle. By comparing real-time voltage profiles of donor and receiver batteries, the FLC automatically determines the current direction and optimal phase shift angle without requiring complex mathematical modelling. Beyond emergency charging, this technology enables EVs to function as a mobile, distributed energy storage system within Smart Grids. It optimizes microgrid management in commercial hubs by sharing power autonomously, preventing transformer overload during peak demand. This approach ensures that decentralized energy sharing is both reliable and commercially viable.
Authors - Vladislav Vasilev, Georgi Iliev Abstract - In this paper we derive a new estimate of the channel bit rate. The estimates is a special transformation of the main EVT theorem that is particularly designed for use in telecommunication automated systesm meaning it’s robust to noise, computationally cheep, needs very few data points and no manual validation. Due to the EVT methodology we can evaluate if the bit rate can keep dropping indefinitely or if it has a guaranteed minimum value. The method is relatively fast because it uses Newton’s interpolation instead of hypothesis testing or regression.
Authors - Deepak sharma, Pankajkumar Anawade, Anurag Luharia, Gaurav Mishra, Akshit Yadav Abstract - The exponential growth of cybercrime, cloud-native infrastructures, Internet of Things (IoT) ecosystems, encrypted communications, and AI enabled adversarial techniques has fundamentally challenged traditional digital forensic methodologies. Conventional forensic frameworks developed for static systems cannot scale to high-velocity, heterogeneous data environments. This study proposes and empirically evaluates a lifecycle-oriented AI-enhanced digi tal forensic architecture integrating machine learning (ML), deep learning (DL), graph analytics, and explainable AI (XAI). Across benchmark datasets in intru sion detection, malware classification, multimedia authentication, and textual intelligence extraction, AI-enhanced systems significantly improved detection accuracy (up to 98.3%) and reduced analyst workload (40–60%). However, ad versarial robustness testing and explainability evaluation reveal governance and admissibility challenges. The findings demonstrate that while AI enhances scalability and zero-day detection, its responsible adoption requires reproduci bility controls, interpretability safeguards, and alignment with legal standards such as Daubert.
Authors - Netochukwu Onyiaji, Lukas Cironis, Leonid Bogachev, Liqun Liu, Janos Gyarmati-Szabo, Roy A. Ruddle Abstract - This study examines the adoption of AI-enabled hotel chatbots by investigating the role of technology readiness and consumer perceptions in shaping guests’ attitudes and behavioral intentions. Drawing upon the Technology Acceptance Model (TAM) and the Technology Readiness Index (TRI 2.0), the research integrates technological and psychological determinants of AI service adoption in hospitality settings. Data were collected from 270 hotel guests who had previously interacted with chatbots in four-star hotels in Jakarta and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results indicate that technology readiness, perceived convenience, and perceived information quality significantly influence guests’ attitudes toward AI hotel chatbots. However, attitude and perceived convenience do not directly translate into adoption intention, revealing an attitude–intention gap. The model explains 61% of the variance in attitude and 38% in behavioral intention. These findings extend technology adoption literature by highlighting the role of psychological readiness and service perceptions in shaping guest adoption of AI-enabled hospitality technologies.
Authors - Aung Nyein Chan Paing, Sudhir Kumar Sharma Abstract - This paper presents a semantic video search system that supports natural lan guage querying over video content using vision–language models and vector similarity search. The proposed system processes videos offline by extract ing representative frames through similarity-based filtering, generating textual descriptions using a pre-trained BLIP (Bootstrapping Language–Image Pre training) image captioning model, and encoding the captions into dense vector embeddings. These embeddings are indexed in a vector database to enable effi cient retrieval of relevant video segments based on textual queries. The system architecture comprises a Python-based backend with GPU acceleration for video processing and a web-based interface for query interaction. Experimental obser vations indicate that similarity-based frame filtering reduces redundant frames by approximately 50–70% while preserving semantic information. Qualitative eval uation demonstrates that the system effectively retrieves semantically relevant video timestamps in response to natural language queries. The proposed frame work serves as a modular prototype for content-based video retrieval and semantic video analysis applications.
Authors - Qing Li Abstract - Intrusion Detection Systems (IDS) are critical for cybersecurity, yet conventional approaches based on machine learning often suffer from limited explainability, high computational cost, and scalability issues. We introduce Recommendation-Driven IDS (RD-IDS), a novel framework that models security events and detection rules as a hypergraph, reformulating intrusion detection as a structured recommendation problem. Detection is achieved through the computation of minimal transversals, identifying minimal and actionable sets of security measures. RD-IDS is formally defined with hypergraph representations, recommendation semantics, and UML-based architecture, ensuring traceability and modularity. Algorithmically, we leverage minimal transversal enumeration, including the Fredman–Khachiyan dualization method, and analyze temporal and spatial complexity, demonstrating that structural reductions and active set optimizations mitigate overhead. RD-IDS offers deterministic, explainable, and scalable detection by construction, providing a principled alternative to machine learning-centric IDS. This work establishes the formal and algorithmic foundations of RD-IDS, laying the groundwork for practical implementation and experimental validation in a companion study.
Authors - Ahmed Alansary, Molham Mohamed, Ali Hamdi Abstract - Quantum secret sharing (QSS) scheme is a cryptographic protocol for sharing a secret among parties in a secure way, such that only the set of all authorized parties can reconstruct the secret using the quantum information. In this manuscript, a multi-secret sharing scheme (namely, qMSS) is proposed and analyzed utilizing a quantum error-correcting code (CSS code) for generating and reconstructing shares. qMSS generates n quantum shares of an m(≤ k)-bit classical secret using [[n,k,d]]q CSS code and distributes shares among n participants. This work generalizes the sharing of one-bit classical secret, utilizing CSS codes, proposed by Sarvepalli and Klappenecker. The set of all authorized parties is identified by minimal codewords associated with the classical code underlying the CSS code. The proposed qMSS is a perfect multi-secret sharing scheme due to the set of all unauthorized parties is unable to obtain any information about the secret.
