Special Issues
Table of Content

Safe and Secure Artificial Intelligence

Submission Deadline: 01 August 2025 (closed) View: 3245 Submit to Journal

Guest Editors

Prof. Wen-Chen Hu

Email: wen.chen.hu@und.edu

Affiliation: School of Electrical Engineering and Computer Science, University of North Dakota, Grand Forks 58202, United States

Homepage:

Research Interests: Handheld/Mobile/Smartphone/Spatial Computing, Location-Based Services, Web-Enabled Information System, Electronic and Mobile Commerce Systems, Web Technologies

图片1.png


Dr. Sanjaikanth E Vadakkethil Somanathan Pillai

Email: s.evadakkethil@und.edu

Affiliation: School of Electrical Engineering and Computer Science, University of North Dakota, Grand Forks 58202, United States

Homepage:

Research Interests: Artificial Intelligence, Machine Learning, Security,Privacy, Mobile Networks

图片2.png


Prof. Piyush Kumar Pareek

Email: piyush.kumar@nmit.ac.in

Affiliation: Professor and Head (IPR Cell), Nitte Meenakshi Institute of Technology, Bengaluru, India

Homepage:

Research Interests: Software Engineering, Data Science, Data Compression, Image Processing, Deep Learning

图片3.png


Summary

1) Issue Introduction: Background and Importance

As AI technologies increasingly impact critical areas like healthcare, finance, and defense, the need for safe and secure AI systems is more important than ever. These systems bring powerful benefits but also introduce significant risks, including data privacy breaches, adversarial attacks, and algorithmic biases. Such challenges threaten both individual users and society as a whole, raising concerns about the reliability and ethical alignment of AI technologies. Addressing these issues is essential to ensure that AI systems are not only innovative but also robust, transparent, and trustworthy.


2) Aim and Scope of the Special Issue

This special issue aims to bring together interdisciplinary research and reviews that address the core challenges of AI safety and security. We seek to foster a multidisciplinary conversation on both theoretical and practical aspects, covering emerging risks, best practices, and technological innovations that enhance the reliability of AI systems. Contributions from computer science, engineering and ethics are encouraged, and topics may range from novel algorithms to case studies and empirical research. This issue is open to submissions that explore both technical solutions and broader implications for society, emphasizing research that contributes to a safer, more secure AI landscape.


3) Suggested Themes

-Trustworthy and Explainable AI

-Adversarial Machine Learning

-Data Privacy and Security

-Ethics and Governance of AI

-AI in Critical Infrastructure

-Bias and Fairness in AI

-AI Robustness and Reliability

-Secure Federated Learning

-AI and Cybersecurity

-Human-in-the-Loop AI 


Keywords

Artificial Intelligence, Machine Learning, Security, Privacy, Fraud Detection, Secure Communication

Published Papers


  • Open Access

    ARTICLE

    DriftXMiner: A Resilient Process Intelligence Approach for Safe and Transparent Detection of Incremental Concept Drift in Process Mining

    Puneetha B. H., Manoj Kumar M. V., Prashanth B. S., Piyush Kumar Pareek
    CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-33, 2026, DOI:10.32604/cmc.2025.067706
    (This article belongs to the Special Issue: Safe and Secure Artificial Intelligence)
    Abstract Processes supported by process-aware information systems are subject to continuous and often subtle changes due to evolving operational, organizational, or regulatory factors. These changes, referred to as incremental concept drift, gradually alter the behavior or structure of processes, making their detection and localization a challenging task. Traditional process mining techniques frequently assume process stationarity and are limited in their ability to detect such drift, particularly from a control-flow perspective. The objective of this research is to develop an interpretable and robust framework capable of detecting and localizing incremental concept drift in event logs, with a… More >

  • Open Access

    ARTICLE

    Enhancing Ransomware Detection with Machine Learning Techniques and Effective API Integration

    Asad Iqbal, Mehdi Hussain, Qaiser Riaz, Madiha Khalid, Rafia Mumtaz, Ki-Hyun Jung
    CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 1693-1714, 2025, DOI:10.32604/cmc.2025.064260
    (This article belongs to the Special Issue: Safe and Secure Artificial Intelligence)
    Abstract Ransomware, particularly crypto-ransomware, remains a significant cybersecurity challenge, encrypting victim data and demanding a ransom, often leaving the data irretrievable even if payment is made. This study proposes an early detection approach to mitigate such threats by identifying ransomware activity before the encryption process begins. The approach employs a two-tiered approach: a signature-based method using hashing techniques to match known threats and a dynamic behavior-based analysis leveraging Cuckoo Sandbox and machine learning algorithms. A critical feature is the integration of the most effective Application Programming Interface call monitoring, which analyzes system-level interactions such as file More >

  • Open Access

    REVIEW

    A Detailed Review of Current AI Solutions for Enhancing Security in Internet of Things Applications

    Arshiya Sajid Ansari, Ghadir Altuwaijri, Fahad Alodhyani, Moulay Ibrahim El-Khalil Ghembaza, Shahabas Manakunnath Devasam Paramb, Mohammad Sajid Mohammadi
    CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 3713-3752, 2025, DOI:10.32604/cmc.2025.064027
    (This article belongs to the Special Issue: Safe and Secure Artificial Intelligence)
    Abstract IoT has emerged as a game-changing technology that connects numerous gadgets to networks for communication, processing, and real-time monitoring across diverse applications. Due to their heterogeneous nature and constrained resources, as well as the growing trend of using smart gadgets, there are privacy and security issues that are not adequately managed by conventional security measures. This review offers a thorough analysis of contemporary AI solutions designed to enhance security within IoT ecosystems. The intersection of AI technologies, including ML, and blockchain, with IoT privacy and security is systematically examined, focusing on their efficacy in addressing… More >

  • Open Access

    ARTICLE

    Leveraging Safe and Secure AI for Predictive Maintenance of Mechanical Devices Using Incremental Learning and Drift Detection

    Prashanth B. S, Manoj Kumar M. V., Nasser Almuraqab, Puneetha B. H
    CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 4979-4998, 2025, DOI:10.32604/cmc.2025.060881
    (This article belongs to the Special Issue: Safe and Secure Artificial Intelligence)
    Abstract Ever since the research in machine learning gained traction in recent years, it has been employed to address challenges in a wide variety of domains, including mechanical devices. Most of the machine learning models are built on the assumption of a static learning environment, but in practical situations, the data generated by the process is dynamic. This evolution of the data is termed concept drift. This research paper presents an approach for predicting mechanical failure in real-time using incremental learning based on the statistically calculated parameters of mechanical equipment. The method proposed here is applicable… More >

Share Link