Article
Computer Science, Artificial Intelligence
Muhammad Amin, Duri Shehwar, Abrar Ullah, Teresa Guarda, Tamleek Ali Tanveer, Sajid Anwar
Summary: The use of smart and connected devices has increased rapidly, with Android and IoT becoming the main platforms. Due to the large number of Android applications, Android has become a target for malware attacks. This study proposes a deep learning based feature detector for malware detection and achieves significant results.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Alejandro Guerra-Manzanares, Marcin Luckner, Hayretdin Bahsi
Summary: The study presents a novel method to detect and address concept drift in Android malware detection, maintaining high performance over an extended period and minimizing the need for model retraining efforts.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Farhath Zareen, Mateus Augusto Fernandes Amador, Robert Karam
Summary: With the rapid growth and usage of IoT devices, protecting device security becomes increasingly important. This paper introduces a hardware-based malware detection approach that alleviates power and performance overheads. The method is designed for low-power, resource constrained, and network facing embedded devices, capable of detecting botnet activity with high accuracy.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2022)
Article
Computer Science, Artificial Intelligence
Durmus Ozkan Sahin, Oguz Emre Kural, Sedat Akleylek, Erdal Kilic
Summary: Mobile and wireless technology have made mobile devices an important part of our lives. However, Android, being the leading operating system, is also the most targeted platform by attackers. This study proposes a machine learning-based malware detection system that uses feature selection methods to distinguish Android malware from benign applications.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Jeonggeun Jo, Jaeik Cho, Jongsub Moon
Summary: Artificial intelligence (AI) is widely used in cybersecurity, especially for detecting malicious applications. However, the lack of transparency in AI models poses a challenge in understanding and trusting the results. This paper proposes a method of using a Vision Transformer (ViT) for detecting malware and extracting malicious behavior, providing high detection accuracy and interpretability.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Yi Wang, Tao Li, Xiaojie Liu, Jian Yao
Summary: This study develops an improved adaptive clonal selection algorithm with multiple differential evolution strategies. The algorithm introduces an adaptive mutation strategy pool, an adaptive population resizing method, and detection methods for premature convergence and stagnation. Experimental results demonstrate that the proposed method outperforms state-of-the-art clonal selection algorithms and differential evolution algorithms.
INFORMATION SCIENCES
(2022)
Review
Computer Science, Information Systems
Praneet Saurabh, Bhupendra Verma
Summary: Negative selection, with its ability to detect self and non-self in a given problem space, has attracted research interest for complex problem solving in various application areas. It is particularly suitable and compelling for anomaly detection due to its adaptability, learning, robustness, and fast response. This review paper critically evaluates and categorizes various negative selection taxonomies, representations, and matching techniques and aims to establish future research areas for addressing complex security challenges.
COMPUTER SCIENCE REVIEW
(2023)
Article
Computer Science, Hardware & Architecture
Farnood Faghihi, Mohammad Zulkernine
Summary: RansomCare is introduced as a data-centric detection and mitigation method against smartphone cryptoransomware, capable of real-time detection and neutralization of ransomware while preserving data privacy. With a reliance on user data structure and data entropy, RansomCare can quickly and accurately detect crypto-ransomware on smartphones.
Article
Computer Science, Artificial Intelligence
Yun Ji Kim, Weonwoo Nam, Jongsoo Lee
Summary: An imbalance between normal and abnormal signal data poses a key challenge in anomaly detection. This study presents a multiclass anomaly detection algorithm that combines the principles of negative selection algorithm (NSA) and clonal selection algorithm (CSA). The algorithm is enhanced with unsupervised and semi-supervised learning algorithms to conveniently detect anomalies in real industrial sites, improving classification accuracy and reducing run time.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Jinyin Chen, Xueke Wang, Mengmeng Su, Xiang Lin
Summary: A novel hybrid detector generation algorithm FCAIS-HD is proposed in this study to address challenges in artificial immune systems, demonstrating superior performance in noise exclusion, detection rate, and parameter sensitivity compared to other algorithms through comprehensive experiments on both simulation and real world data sets.
APPLIED INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Soodeh Hosseini, Hossein Seilani
Summary: The artificial immune system, derived from the biological immune system, is used for anomaly process detection. A new combining technique of negative selection and classification algorithm is proposed to increase accuracy and decrease training time. The technique is evaluated on CICIDS 2017 and NSL-KDD datasets for detecting anomaly processes.
Article
Computer Science, Hardware & Architecture
Kutub Thakur, Hamed Alqahtani, Gulshan Kumar
Summary: The intelligent system IDGADS is capable of quickly detecting algorithmically generated domains with 99% accuracy based on easy-to-compute features of real domain name system (DNS) traffic. It can serve as the first line of defense in a security stack for validating DNS queries.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
A. Abid, M. T. Khan, I. U. Haq, S. Anwar, J. Iqbal
Summary: Fault detection is crucial for the safety of technical processes and systems. This paper presents an improved negative selection algorithm using specialized detectors, which enhances the accuracy and efficiency of fault detection while reducing online anomaly detection time.
IETE JOURNAL OF RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Lingjie Li, Qiuzhen Lin, Ke Li, Zhong Ming
Summary: A novel vertical distance-based clonal selection mechanism (VD-MOIA) is proposed in this study to improve population diversity in MOIAs. By decomposing the target MOP into a set of subproblems and executing the vertical distance-based clonal selection mechanism, good results are achieved in multiobjective optimization problems.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Information Systems
Parnika Bhat, Sunny Behal, Kamlesh Dutta
Summary: This paper proposes a precise dynamic analysis approach to identify a variety of malicious attacks. The proposed method focuses on behavioral analysis of malware and uses features such as system calls, binders, and complex Android objects. By employing feature selection and stacking machine learning algorithms, efficient malware detection and classification with an accuracy rate of 98.08% is achieved.
COMPUTERS & SECURITY
(2023)