AI for Network Security System

In an increasingly interconnected world, cybersecurity threats are becoming more sophisticated and dynamic. Traditional security systems often rely on predefined rules and patterns, which can fail to detect subtle or evolving anomalies. Insider threats and external breaches remain significant challenges, as these threats exploit gaps in existing security frameworks, leaving organisations vulnerable to data theft, service disruption, and reputational damage.

Market Gaps: Limitations of Traditional Security Systems

While existing Security Information and Event Management (SIEM) systems provide valuable tools for monitoring and analysis, they are often limited in their ability to adapt to complex and nuanced behaviours that signal potential threats. Current technologies lack the capability to effectively integrate diverse data sources, including physical, social, and cyber domains, into a unified and actionable framework. Moreover, few solutions make use of advanced AI to proactively detect and mitigate threats in real-time.

The Solution: Context-Aware Security with CASPER AI

Project duration:

12 months

Project status:

Completed

100%

Total funding:

$100,000

Project leaders:

Professor Ren Ping Liu – University of Technology Sydney

Dr Xu Wang – University of Technology Sydney

CASPER AI

Led by Professor Ren Ping Liu and Dr. Xu Wang from the University of Technology Sydney, the CIN’s AI for Network Security System project introduces CASPER AI, short for Context-Aware Security Policy Enforcement and Response.

Final presentation:

21 November 2025

CASPER AI represents a new generation of adaptive cybersecurity technology. Built upon Large Language Models (LLMs) and multimodal reasoning, the system analyses information across diverse data sources such as ID systems, HR records, travel and expense data and network logs to detect anomalies that may indicate insider threats or external breaches.

Innovation, Novelty and Key Features

CASPER AI moves cybersecurity beyond reactive monitoring. By combining LLMs, multimodal analytics and policy-aware decision-making, it provides an intelligent and adaptive approach to threat detection and response.

Key features include:

Context-aware security analysis that interprets behaviours and activities across multiple data domains to identify potential risks before they escalate
Automated policy and process review that enables the system to recommend timely and compliant actions based on an organisation’s internal frameworks
Continuous learning that refines models over time to recognise emerging threats and adapt to evolving operational environments
Identity intelligence that consolidates diverse authentication, access and behavioural data to detect anomalous or fraudulent activity
Integration with existing SIEM systems to enhance accuracy and reduce response times

Applications

CASPER AI is designed to help government and service providers protect communities through early detection and coordinated response to cybersecurity risks. Its applications span a wide range of domains, including:

Securing government service accounts by detecting anomalous logins and unusual account activity such as access from unexpected locations or instances of impossible travel
Preventing identity misuse and fraud through analysis across authentication, claims and travel data, allowing agencies to act before stolen credentials are exploited
Guarding against scams and fraudulent communications by supporting verification platforms for suspicious calls, SMS or emails, enabling residents to confirm whether a message is genuine before acting

Together, these capabilities demonstrate how CASPER AI can transform cybersecurity from reactive monitoring to proactive protection, ensuring that security systems work for everyone, including those in regional and remote communities with limited access to technical support