Eleena Sarah Mathew^*

Journal on Artificial Intelligence, Vol.7, pp. 347-363, 2025, DOI:10.32604/jai.2025.069841 - 06 October 2025

Abstract This review paper explores advanced methods to prompt Large Language Models (LLMs) into generating objectionable or unintended behaviors through adversarial prompt injection attacks. We examine a series of novel projects like HOUYI, Robustly Aligned LLM (RA-LLM), StruQ, and Virtual Prompt Injection that compel LLMs to produce affirmative responses to harmful queries. Several new benchmarks, such as PromptBench, AdvBench, AttackEval, INJECAGENT, and RobustnessSuite, have been created to evaluate the performance and resilience of LLMs against these adversarial attacks. Results show significant success rates in misleading models like Vicuna-7B, LLaMA-2-7B-Chat, GPT-3.5, and GPT-4. The review highlights limitations… More >

Ragava Raja R^1,2,*, Girish Khanna R³

Journal on Artificial Intelligence, Vol.7, pp. 301-327, 2025, DOI:10.32604/jai.2025.069693 - 22 September 2025

Abstract Packaging materials are indispensable in modern industries but also significantly contribute to environmental degradation, resource consumption, and waste generation. This systematic review critically assesses the integration of artificial intelligence (AI), life cycle sustainability assessment (LCSA) following ISO 14040 standards, and circularity mapping to overcome sustainability barriers in packaging. The study identifies environmental, economic, and social hotspots across the life cycle stages of packaging materials by examining real-world case studies such as Coca-Cola’s adoption of recycled PET bottles and Unilever’s commitment to 100% recyclable plastic. AI technologies highlight transformative tools for optimising resource allocation, enhancing waste… More >

Charles Munyao^*, John Ndia

Journal on Artificial Intelligence, Vol.7, pp. 329-346, 2025, DOI:10.32604/jai.2025.069226 - 22 September 2025

Abstract The natural language processing (NLP) domain has witnessed significant advancements with the emergence of transformer-based models, which have reshaped the text understanding and generation landscape. While their capabilities are well recognized, there remains a limited systematic synthesis of how these models perform across tasks, scale efficiently, adapt to domains, and address ethical challenges. Therefore, the aim of this paper was to analyze the performance of transformer-based models across various NLP tasks, their scalability, domain adaptation, and the ethical implications of such models. This meta-analysis paper synthesizes findings from 25 peer-reviewed studies on NLP transformer-based models,… More >

Meenakshi S. Patil^1,*, Rajesh B. Ghongade², Hemant B. Dhonde³

Journal on Artificial Intelligence, Vol.7, pp. 289-300, 2025, DOI:10.32604/jai.2025.069500 - 12 September 2025

Abstract This study seeks to establish a novel, semi-automatic system that utilizes Industry 4.0 principles to effectively determine both acceptable and rejectable concrete cubes with regard to their failure modes, significantly contributing to the dependability of concrete quality evaluations. The study utilizes image processing and machine learning (ML) methods, namely object detection models such as YOLOv8 and Convolutional Neural Networks (CNNs), to evaluate images of concrete cubes. These models are trained and validated on an extensive database of annotated images from real-world and laboratory conditions. Preliminary results indicate a good performance in the classification of concrete More >

Geoffry Mutiso^*, John Ndia

Journal on Artificial Intelligence, Vol.7, pp. 275-288, 2025, DOI:10.32604/jai.2025.069768 - 05 September 2025

Abstract Tomato leaf diseases significantly reduce crop yield; therefore, early and accurate disease detection is required. Traditional detection methods are laborious and error-prone, particularly in large-scale farms, whereas existing hybrid deep learning models often face computational inefficiencies and poor generalization over diverse environmental and disease conditions. This study presents a unified U-Net-Vision Mamba Model with Hierarchical Bottleneck Attention Mechanism (U-net-Vim-HBAM), which integrates U-Net’s high-resolution segmentation, Vision Mamba’s efficient contextual processing, and a Hierarchical Bottleneck Attention Mechanism to address the challenges of disease detection accuracy, computational complexity, and efficiency in existing models. The model was trained on More >

Syed Sajid Ullah^1,*, Muhammad Zunair Zamir², Ahsan Ishfaq², Salman Khan¹

Journal on Artificial Intelligence, Vol.7, pp. 255-274, 2025, DOI:10.32604/jai.2025.069008 - 29 August 2025

Abstract Accurate vehicle detection is essential for autonomous driving, traffic monitoring, and intelligent transportation systems. This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module, Convolutional Block Attention Module (CBAM), and Deformable Convolutional Networks v2 (DCNv2). The Ghost Module streamlines feature generation to reduce redundancy, CBAM applies channel and spatial attention to improve feature focus, and DCNv2 enables adaptability to geometric variations in vehicle shapes. These components work together to improve both accuracy and computational efficiency. Evaluated on the KITTI dataset, the proposed model achieves 95.4% mAP@0.5—an 8.97% gain over standard YOLOv8n—along with 96.2% More >

Michael Juma Ayuma¹, Shem Mbandu Angolo^1,*, Philemon Nthenge Kasyoka^2,*

Journal on Artificial Intelligence, Vol.7, pp. 205-254, 2025, DOI:10.32604/jai.2025.067361 - 19 August 2025

Abstract The exponential growth of Internet of Things (IoT) devices has introduced significant security challenges, particularly in securing token-based communication protocols used for authentication and authorization. This survey systematically reviews the vulnerabilities in token transmission within IoT environments, focusing on various sophisticated attack vectors such as replay attacks, token hijacking, man-in-the-middle (MITM) attacks, token injection, and eavesdropping among others. These attacks exploit the inherent weaknesses of token-based mechanisms like OAuth, JSON Web Tokens (JWT), and bearer tokens, which are widely used in IoT ecosystems for managing device interactions and access control. The impact of such attacks… More >

Mohammed Moawad Alenazi^*

Journal on Artificial Intelligence, Vol.7, pp. 143-176, 2025, DOI:10.32604/jai.2025.066067 - 27 June 2025

Abstract This paper presents a novel machine learning (ML) enhanced energy management framework for residential microgrids. It dynamically integrates solar photovoltaics (PV), wind turbines, lithium-ion battery energy storage systems (BESS), and bidirectional electric vehicle (EV) charging. The proposed architecture addresses the limitations of traditional rule-based controls by incorporating ConvLSTM for real-time forecasting, a Twin Delayed Deep Deterministic Policy Gradient (TD3) reinforcement learning agent for optimal BESS scheduling, and federated learning for EV charging prediction—ensuring both privacy and efficiency. Simulated in a high-fidelity MATLAB/Simulink environment, the system achieves 98.7% solar/wind forecast accuracy and 98.2% Maximum Power Point… More >

Saurabh Sanjay Singh^*, Rahul Joshi, Deepak Gupta

Journal on Artificial Intelligence, Vol.7, pp. 177-203, 2025, DOI:10.32604/jai.2025.065078 - 30 June 2025

Abstract This paper addresses the challenge of energy-conscious scheduling in modern manufacturing by formulating and solving the Energy-Conscious Flexible Job Shop Scheduling Problem. In this problem, each job has a fixed sequence of operations to be performed on parallel machines, and each operation can be assigned to any capable machine. The problem statement aims to schedule every job in a way that minimizes the total energy consumption of the job shop. The paper’s primary objective is to develop a reinforcement learning-based scheduling framework using the Advantage Actor-Critic algorithm to generate energy-efficient schedules that are computationally fast… More >

Muhammad Naeem^*, Abdul Majid

Journal on Artificial Intelligence, Vol.7, pp. 115-141, 2025, DOI:10.32604/jai.2025.062446 - 30 May 2025

Abstract Brain tumor identification is a challenging task in neuro-oncology. The brain’s complex anatomy makes it a crucial part of the central nervous system. Accurate tumor classification is crucial for clinical diagnosis and treatment planning. This research presents a significant advancement in the multi-classification of brain tumors. This paper proposed a novel architecture that integrates Enhanced ResNeXt 101_32×8d, a Convolutional Neural Network (CNN) with a multi-head self-attention (MHSA) mechanism. This combination harnesses the strengths of the feature extraction, feature representation by CNN, and long-range dependencies by MHSA. Magnetic Resonance Imaging (MRI) datasets were employed to check… More >