Search
18 articles for “adversarial machine learning”
-
Adversarial Attacks on Machine Learning Models in Cybersecurity: A Systematic Literature Review
Abstract: Adversarial machine learning (AML) is a field that is growing swiftly, especially as machine learning models are employed more and more in places where security is critical. This review goes into great depth over 746 publications from the Scopus database, with an emphasis on the connection between AML and network security. Using Biblioshiny and Scopus tools, we looked at trends in publications, study fields, productive authors, collaboration networks, and theme …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 13, Issue 1, 2025 · pp. 23–38 Read article
-
Navigating the Dual Edge: A Comprehensive Technical Survey of Security, Privacy, and Countermeasures in the Era of Artificial Intelligence
Abstract: Artificial Intelligence (AI) is seamlessly weaved into vital sectors such as self-driving cars, high-speed trading systems, and defense strategies, it has triggered a counterintuitive development in advanced cyber-attacks. This survey paper attempts to perform an in-depth technical analysis on “AI Attack Surface.” There are threats across three main vectors. Data Integrity Attacks focuses specifically examining ‘Clean Label’ poisoning and backdoor injection. Model Confidentiality Breaches is discussing the mathematics behind Model …
Published in Journal of Operating Systems Development & Trends · Vol. 13, Issue 1, 2026 Read article
-
Assessing the Robustness of Machine Learning Models for Wireless Intrusion Detection Under Adversarial Traffic Perturbations
Abstract: As the Internet of Things (IoT) devices and wireless communication networks continue to grow rapidly, protecting systems from cyber threats has become increasingly important. Machine learning–based intrusion detection systems (IDS) have shown strong potential in detecting abnormal and malicious network activities, yet their effectiveness and resilience when facing adversarial attacks are still not sufficiently explored. This research evaluates Machine Learning (ML) models–XGBoost, random forest, and multi-layer perceptron (MLP)—in detecting attacks …
Published in International Journal of Wireless Security and Networks · Vol. 4, Issue 1, 2026 · pp. 29–34 Read article
-
Role of Machine Vision in Autonomous Vehicles: A Review
Abstract: The integration of machine vision in autonomous vehicles (AVs) is a critical advancement in the field of intelligent transportation systems. Machine vision systems enable AVs to perceive their environment, understand road conditions, detect obstacles, and make real-time decisions necessary for safe navigation. These systems rely heavily on image processing techniques, which have evolved significantly over the past decade, leading to improved performance in complex driving scenarios. These developments are largely …
Published in Trends in Machine design · Vol. 12, Issue 1, 2025 · pp. 38–43 Read article
-
A Comparison of Different Generative AI Models
Abstract: Generative models have significantly advanced the field of artificial intelligence by allowing machines to produce complex and realistic outputs such as images, text, and other forms of data. Among the leading frameworks in this domain are generative adversarial networks (GANs), variational autoencoders (VAEs), and architectures based on Transformers. Each model offers specific benefits and drawbacks concerning design structure, training demands, and range of applications. This paper provides a detailed comparison …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 13, Issue 1, 2025 · pp. 16–22 Read article
-
Bias Detection and Accuracy Enhancement in Voice-based Banking Authentication Using Deep Learning
Abstract: Biometric systems have become an integral part of how many people access banking services today, and voice verification systems can be a secure and easy-to-use source of banking authentication that does not require any physical contact with the bank or any other person. From the security perspective, these systems would normally provide an effective means of identifying an individual but frequently exhibit bias with respect to demographics such as the …
Published in International Journal of Information Security Engineering · Vol. 4, Issue 2, 2026 Read article
-
A Review on the Impact of Artificial Intelligence on Cybersecurity
Abstract: When it comes to protecting against cyber threats, the use of AI is changing everything. Thanks to AI-powered technologies, organizations can now better foresee and handle potential intrusions. These solutions provide exceptional capabilities in identifying threats, monitoring in real time, and delivering predictive insights. But, with these innovations come significant hazards and difficulties, necessitating thoughtful deliberation and preventative measures. Artificial intelligence's impact on cybersecurity is explored in this article, looking …
Published in Journal of Artificial Intelligence Research & Advances Read article
-
Development of a Generative AI Model for Early Detection and Prevention of Electrical Faults in Thermal Power Plants
Abstract: Electrical faults in thermal power plants can lead to severe equipment damage, production downtime, and safety hazards if not detected in advance. This study presents the development of a Generative Artificial Intelligence (GenAI) model for the early detection and prevention of electrical faults using predictive analytics. The proposed framework integrates Generative Adversarial Networks (GANs) with deep learning (CNN) and machine learning algorithms (Random Forest, Logistic Regression) to enhance data diversity, …
Published in International Journal of Energy and Thermal Applications · Vol. 4, Issue 1, 2026 · pp. 1–10 Read article
-
Transfer Learning in Deep Learning Models for Medical Imaging: Utilizing Pretrained Models to Improve Performance in Medical Image Analysis
Abstract: Transfer learning is now a trending technique in deep learning, especially in medical imaging. This technique solves landmark problems by utilizing the pre-trained models, including the limited availability of the annotated medical data and the time-consuming computational costs of training deep learning models from scratch. The generalizability of deep models could increase diagnostic precision for specific medical tasks, require fewer samples to train, and take less time to train due …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 1, 2025 · pp. 67–85 Read article
-
Enhancing Smart Grid Security: Machine Learning Approaches for Detecting Anomalies
Abstract: The integration of Information and Communication Technology (ICT) with traditional electric grids has led to the development of smart grids. However, this integration has also increased the risk of anomalies, such as cyber-attacks, metering fraud, electricity theft etc. False Data Injection Attacks are a class of cyber-attacks against power grid monitoring systems, where adversaries can inject false data to manipulate the grid’s operation. Metering frauds pertain to malicious customers com- …
Published in Trends in Electrical Engineering · Vol. 14, Issue 2, 2024 · pp. 10–19 Read article
-
AI-Based Threat Detection in Cloud Platforms
Abstract: This research work delves into the transformative role AI has come to assume for enhanced threat detection in the cloud ecosystem. The conventional security frameworks, which form the basis for many architectures, are several steps behind actualizing the rapidly evolving cyber threat landscape, exposing critical weaknesses in the areas of accuracy, adaptability, and speed of response. Initially, the study sets forth the problems with the old-school approaches to threat detection …
Published in Journal Of Network security · Vol. 13, Issue 3, 2025 · pp. 01–10 Read article
-
A Survey On Leveraging Machine Learning for Phishing Attack Prediction and Detection
Abstract: Phishing is one of the biggest cybersecurity threats that exploits user trust by masquerading as a legitimate site or email to steal personal and sensitive information. A state- of-the-art-phishing detection systems survey, this review showcases the evolution from traditional list-based techniques, including blacklisting and whitelisting to machine learning and deep learning models. While list-based systems cannot evolve to detect new and zero-day attacks, the ML algorithms of Decision Tree, Random …
Published in Journal of Microelectronics and Solid State Devices · Vol. 12, Issue 3, 2025 · pp. 1–10 Read article
-
Cyberattack Detection and Prevention Using Empowering AI Tools
Abstract: With more organizations entering the digital transformation sphere, the opportunities and risks in cyberspace have increased and gone up in levels of sophistication and occurrence. Many of these developments are attributed to the limits of existing cyber security solutions where addressing new threats requires advanced detection technologies and techniques. Cyber threats gained a new meaning and dimension with artificial intelligence (AI) coming into play in ways that supplement security systems …
Published in International Journal of Information Security Engineering · Vol. 2, Issue 2, 2024 · pp. 1–7 Read article
-
TensorFlow: Architecture, Applications, and Future Challenges
Abstract: TensorFlow, an open-source machine learning platform created by Google, has revolutionized how artificial intelligence (AI) systems are built and implemented. Designed to support scalable and flexible model training across CPUs, GPUs, and TPUs, TensorFlow enables researchers and developers to construct advanced deep learning models with efficiency and precision. This study provides an in-depth examination of TensorFlow's architecture, including its use of dataflow graphs and tensor-based computation. We explore its adaptability …
Published in Journal of Open Source Developments · Vol. 12, Issue 2, 2025 · pp. 41–50 Read article
-
Robustness of Deepfake Detection Systems Against Adversarial Attacks
Abstract: This paper explores a deep learning system to detect deepfake videos, a common type of fake media. With the use of sophisticated methods such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), our system can reliably discern between authentic and altered videos. It analyzes both the images and the audio in videos to find signs of deepfake manipulation. We process video frames and audio, extract features with CNNs …
Published in Journal of Instrumentation Technology & Innovations · Vol. 14, Issue 2, 2024 Read article
-
Differential Privacy-Aware Data Sanitization for Multi-Level Security
Abstract: Multi-level security (MLS) models are fundamental for enforcing mandatory access control in high-security environments such as government, military, healthcare, and finance. However, traditional MLS frameworks, including the Bell-LaPadula and Biba models, often create rigid data silos, preventing efficient data utilization. Differential privacy (DP) presents a novel solution by enabling controlled information leakage while preserving confidentiality. By injecting statistical noise into query results, DP allows lower-clearance users to access sanitized versions …
Published in International Journal of Computer Science Languages · Vol. 3, Issue 1, 2025 · pp. 42–52 Read article
-
Machine Learning in Nuclear Medical Applications: A Review of Research Frontiers
Abstract: Nuclear medicine, encompassing PET, SPECT, and targeted radionuclide therapy, generates high-dimensional, quantitative data uniquely suited for machine learning (ML) analysis. This review synthesizes current research applications of ML across six key domains. Positron emission tomography (PET), single-photon emission computed tomography (SPECT), and targeted radionuclide therapy are examples of nuclear medicine modalities that generate high- dimensional, quantitative datasets that are particularly well-suited for machine learning (ML)-driven analysis. These imaging methods provide …
Published in Journal of Nuclear Engineering & Technology · Vol. 16, Issue 1, 2026 · pp. 19–24 Read article
-
Cybersecurity of AI and IoT Integrated for Mechanical Industries
Abstract: By facilitating the concept of Industry 4.0, the intersection of artificial intelligence (AI) and the Internet of Things (IoT) has changed the mechanical industries. When combined, these technologies are advancing process optimization, predictive maintenance, real-time condition monitoring, and smarter automation. In order to give proactive system control and intelligent decision-making, AI algorithms mine large datasets generated via IoT devices for relevant patterns. In the meanwhile, IoT guarantees smooth communication between …
Published in Journal of Mechatronics and Automation · Vol. 12, Issue 2, 2025 · pp. 27–33 Read article