APTs can be very advanced, able to hide within an organization for years, potentially compromising sensitive data and information. Old-fashioned signature-driven security tools don't keep up with the latest and most advanced attacks, and thus require proactive and intel-driven threats detection products. This research aims to design an early prediction and detection system of Advanced Persistent Threat activities with a machine learning system that works on Cyber Threat Intelligence. The architecture pulls together any and all threat intelligence gathered from network traffic logs, security alerts and external sources including Indicators of Compromise that include suspicious IP addresses, malicious website addresses, and other unusual communications. After data preprocessing and feature engineering, machine learning models such as Random Forest, Support Vector Machine, and Gradient Boosting are employed to learn the harmful user actions and foresee potentially high-risk actions. This suggested methodology is tested using the CICIDS2017 and UNSW-NB15 benchmark datasets of cyber security. It was observed from the experimental results that the best results has been obtained by Random Forest classifier with the highest accuracy as 97.8% after the differentiation of the legitimate and harmful activity. The results show that the integration of Cyber Threat Intelligence with machine learning has a significant impact on early threat detection, reduces the number of false-positive alerts and strengthens cyber security efforts to prevent Advanced Persistent Threat attacks.
Maheshwari S, S. Kirubakaran, R. Chitra et al.· 2026 6th International Confe...· 0 citations
The rapid roll-out of 5G communication networks, 5G Users can experience high-speed connections, super low latency and wide-open connectivity with Internet of Things. The 5G infrastructures are based on the distributed architecture, which makes them vulnerable to advanced cyber-attacks such as Distributed Denial-of-Service, Sybil attack, Spoofing attack, Insider attack and Data manipulation attack. The prevailing security paradigm in recent years has been focusing on either intrusion detection or privacy protection, but little effort has been made to achieve a combined and integrated security strategy to construct a proper trust and base the decisions that are taken. In order to overcome the above challenge, the present work introduces the TrustChain-5G system, a safe and secure trust based system, that combines the advantages of Federated Learning, Adaptive Trust Evaluation, Blockchain and Machine Learning for detecting attacks. The trusted behavior economy model constantly monitors node communication patterns, past interactions, security compliance index to identify suspicious nodes in a system. Federated learning can be used to create a collaborative model, keeping privacy intact, while blockchain can be used to store security events (tamper-proof), and trust records. The simulated 5G environment for the evaluation of the framework consisted of 100 network nodes in a mixture of CICIDS2017, CICDDoS2019 and UNSW-NB15 datasets. This is experimentally demonstrated to provide 96.2% accuracy, 95.4% precision, 94.9% recall and a minimum detection delay in various attack scenarios. The results validate the success of the proposed architecture in increasing the efficiency of attacks detection, trust management system, and ensuring security and reliability in future 5G communication network.
A. Ponsangeetha, R. Chitra, P. Sindhu et al.· 2026 6th International Confe...· 0 citations
