Cyber theft Predictive System using AI Prophet: A Multi-Faceted AI Approach

  • Unique Paper ID: 176304
  • Volume: 11
  • Issue: 11
  • PageNo: 7070-7075
  • Abstract:
  • Cyber theft poses a persistent and escalating threat in the digital era, with attackers exploiting system vulnerabilities and user behavior to orchestrate breaches. Traditional cybersecurity measures often fall short in proactively identifying emerging threats, especially in dynamic environments. This paper presents a novel AI-driven approach that integrates Natural Language Processing (NLP) and time-series anomaly detection for predictive cybersecurity. By leveraging transformer-based models like BERT for analyzing threat intelligence feeds, emails, and incident reports, and combining them with machine learning-based time-series models such as Facebook Prophet, our system anticipates potential breaches and identifies anomalous behavior patterns. Experimental evaluation using real-world cybersecurity datasets demonstrates that this hybrid AI framework significantly improves threat detection accuracy and reduces false positives compared to standalone detection methods. The findings highlight the potential of intelligent predictive systems in strengthening cybersecurity defenses and enabling proactive threat mitigation.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 11
  • PageNo: 7070-7075

Cyber theft Predictive System using AI Prophet: A Multi-Faceted AI Approach

Related Articles