Daily Archives: October 31, 2026

Authors: Sphoorthy Reddy Surakanti, Dr. S. Ramachandram

Abstract: The use of IoT devices in huge numbers results in massive amounts of sensitive data being outsource into cloud storage systems, making it necessary to design efficient search schemes over such encrypted data. Phrase Search allows users to retrieve their documents by matching exact sequences of keywords, but existing solutions have not found a good balance between search time, storage space, and privacy loss due to their static design. In this work, we propose an efficient Dynamic Adaptive Bloom Filter based Privacy-Preserving Phrase Search (DABF-PPS) scheme for encrypted IoT cloud data. We introduce a dynamic parameter optimization method to adaptively adjust Bloom filters according to document set properties and queries. A hierarchical n-gram Bloom filter index is designed to allow phrase searches without exposing keyword locations. Furthermore, our solution supports dynamic updating of indices with the help of counting Bloom filter structures and lazy deletion. Our security analysis proves that our solution provides forward and limited backward privacy against chosen-keyword attacks. Our experiments on real-world IoT datasets show that our approach decreases search time and storage space while maintaining acceptable false-positive rates.

DOI: https://doi.org/10.5281/zenodo.23834235

Published by: vikaspatanker

Authors: Vinutha R

Abstract: The emergence of advanced cyber-attacks targeting the latest network infrastructure has highlighted the inefficiencies of signature-based systems employed to detect such attacks, which are unable to recognize new threats due to their lack of adaptability. The current paper offers a machine learning framework for cyber threat detection and network security improvement through real-time application of streaming data analysis techniques together with ensemble learning approaches. The system is based on a hybrid framework comprising of the Random Forest and XGBoost classifiers for detection of known attacks and autoencoder-based anomaly detection method for identifying unknown threats. Feature engineering is used to extract static and behavioral features of the network traffic. In addition, the system includes an adaptive response strategy, which allows the system to dynamically modify the network security policy depending on the threat level. It was shown that the offered system is capable of providing efficient threat detection for different types of attacks, while being computationally efficient enough to be applied in a real-time scenario.

DOI: https://doi.org/10.5281/zenodo.23834126

Published by: vikaspatanker