Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{181069,
        author = {MEGALA R and MR. VIJAYACHANDER},
        title = {ADVANCED AI-DRIVEN CYBERSECURITY FOR AUTONOMOUS ECOSYSTEMS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {3340-3346},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181069},
        abstract = {As robotics and self-sustaining systems 
become an increasing number of incorporated into 
critical infrastructure, ensuring their cybersecurity is 
paramount to guard in opposition to each cyber and 
physical threats. This paper affords an AI-pushed 
cybersecurity 
framework designed to shield 
autonomous ecosystems, combining superior device 
studying and computer vision strategies for 
comprehensive real-time chance detection. The 
machine integrates core modules: a community 
anomaly detection issue primarily based on Long Short
Term Memory (LSTM) neural networks, and a visible 
intrusion detection gadget utilizing YOLOv5 for item 
detection and MiDaS for intensity estimation. The 
LSTM model turned into trained on a large dataset of 
community site visitors, attaining excessive accuracy in 
identifying anomalous styles, even as the imaginative 
and prescient-based totally intrusion detection gadget 
correctly identifies intruders and assesses their spatial 
context via intensity mapping. Both systems' outputs 
are displayed in real-time on an interactive dashboard 
constructed the use of Plotly Dash, permitting operators 
to monitor and respond to threats straight away. The 
proposed framework become tested under simulated 
attack situations, demonstrating low latency, high 
reliability, and sturdy performance throughout both 
cyber and physical chance detection. This paper 
highlights the ability of combining AI and deep getting 
to know for securing self-reliant systems and important 
infrastructure, imparting a proactive technique to 
cybersecurity that addresses each cyber and physical 
vulnerabilities.},
        keywords = {Artificial Intelligence (AI), Cybersecurity,  Robotics, Autonomous Systems, Network Anomaly  Detection, Visual Intrusion Detection, LSTM, YOLOv5,  MiDaS, Deep Learning, Critical Infrastructure, Threat  Detection, Cyber-Physical Security.},
        month = {June},
        }