Journal Of Network security · Vol. 11, No. 4 (2023)
Intrusion Detection, IoT Encryption and Fingerprint Spoofing: Journal of Network Security 11(4)
By STM Journals ·
This issue of the Journal of Network Security looks at protecting systems and data. One paper uses an artificial neural network to detect malicious network traffic. Another designs a lightweight encryption scheme for small Internet of Things devices that cannot afford heavy computation. The third surveys methods for telling a live fingerprint from a fake one in biometric login. Of interest to students and practitioners of cybersecurity.
What's in this issue
-
Intrusion Detection Using ANN Machine Learning for MIM, DOS, BO
How can software spot an attack in network traffic? This study trains an artificial neural network on the NSL-KDD dataset, with feature selection, to classify packets as malicious or benign.
-
Design and Performance Assessment of Light Weight Data Security System for Secure Data Transmission in IoT
Small IoT devices have little power to spare for encryption. This paper presents a lightweight symmetric-key algorithm with a 64-bit block and key, combining Feistel and substitution ideas, and applies it to transmitting images and text with reversible data hiding.
-
Fingerprint Liveliness Detection in Biometric Authentication: A Survey
Fake fingerprints are a growing threat to biometric login. This survey reviews presentation attack detection, the methods that check whether a fingerprint comes from a live finger, and groups them into hardware-based and software-based approaches.