A new artificial intelligence-driven cybersecurity virtual assistant, named CASPER AI (Context-Aware Security Policy Enforcement and Response), has been developed by researchers at the University of Technology Sydney (UTS). This innovative tool is designed to detect threats and guide users and organizations in responding to cyber attacks by integrating information from a variety of sources.
Advancements in Cyber Defense
CASPER AI consolidates organizational data, including details from identity management platforms, human resources records, travel and expense data, and network logs. By correlating these diverse datasets, the system aims to identify anomalies that may indicate insider threats, compromised user accounts, or external breaches. The developers emphasize that CASPER AI can detect unusual activities, such as the creation of fake wireless access points in public areas or suspicious behavior in temporary mobile environments.
“In the demonstration, we showed how CASPER AI detects abnormal activity within business operations, identifies fake wireless access points in public spaces or temporary mobile deployments, and helps teams take fast, policy-compliant security actions,” said Professor Ren Ping Liu, Project Lead at UTS.
This assistant employs large language models and multimodal reasoning, enabling it to analyze various datasets and identify potential cybersecurity threats. Its contextual understanding is one of its main advantages over traditional rule-based cybersecurity tools, which often react to threats without grasping their nuances.
Support for Non-Experts
CASPER AI is crafted to assist users with limited digital experience, thereby reducing the reliance on staff to interpret complex security policies during high-pressure situations. The AI assistant presents clear guidance, which helps users make informed decisions regarding cybersecurity.
“The system reduces the need for staff to interpret complex policies under pressure by presenting the recommended actions in clear, accessible language,” said Liu.
This tool is designed to function across various environments, aiming to lessen the manual workload for security teams. With its user-friendly interface and straightforward outputs, CASPER AI is tailored to support individuals who may struggle with intricate security protocols.
Combatting Online Scams and Fraud
While primarily intended for organizational deployment, CASPER AI also has implications for individual users, particularly those at risk of online scams or with lower digital literacy. The system can detect unusual activity related to personal accounts and provide recommendations in easy-to-understand formats. It assists users in verifying the legitimacy of emails, texts, or calls and in identifying potential identity misuse.
“CASPER AI as a virtual assistant can help people with lower levels of digital literacy and tech experience avoid being caught up in cybercrime, such as phishing and ‘smishing’ (SMS-based) scams,” said Liu.
For sensitive accounts, CASPER AI flags sign-in attempts from new or unauthorized locations, thereby enhancing the security of government and other sensitive accounts.
Part of a Broader Initiative
CASPER AI is part of a series of projects funded through the Connectivity Innovation Network, an initiative supported by the New South Wales Government and led by UTS and the University of Sydney. The network aims to tackle challenges related to digital connectivity and cyber resilience, addressing the increasing complexity of online threats as communities, citizens, and government agencies become more reliant on digital services.
“It’s designed to keep government accounts safe by detecting unusual login attempts or activity, protect people’s identities by connecting information across services to flag potential misuse, and stop scams by giving people a simple way to check if a text, email, or call is genuine before they respond,” Liu explained.
The introduction of CASPER AI exemplifies a significant advancement in cybersecurity technology, offering enhanced support for both organizations and individuals while addressing the rising tide of online threats.
Google Launches AI Security Frameworks and Scam Protection Tools for India’s Digital Economy
Türk Telekom Accelerates AI-Driven Cybersecurity Investments, Blocking 2,620 Attacks in 2023
AI-Powered Cybersecurity Tools Achieve 95% Detection Accuracy in Real-Time Threat Response
AI-Powered Tools Revolutionize Cybersecurity with Real-Time Threat Detection in 2025
SMBs Must Update Cybersecurity Policies as AI Investment Rises, Warns CPA Australia Report
