TELUS Digital, a global leader in digital customer experiences (CX), has announced the launch of Fuel iX™ Fortify, a continuous automated red-teaming solution designed to test generative AI (GenAI) systems at enterprise scale. The application enables organizations to proactively identify vulnerabilities by simulating real-world attack scenarios using advanced adversarial techniques.
As enterprises increasingly adopt GenAI technologies, concerns around safety and security have become critical. Industry research indicates that over two-thirds of organizations (67%) face a shortage of cybersecurity professionals to manage these emerging risks. Fuel iX Fortify addresses this challenge by running thousands of adversarial attacks on AI-powered assistants, copilots, and applications in minutes. The solution leverages an evolving database of adversary tactics, techniques, and procedures derived from the latest research, allowing it to anticipate emerging threats and generate both novel and repeatable tests for continuous safety assessments. Its ability to automatically create attack objectives tailored to a system’s code of conduct ensures robust protection in dynamic GenAI environments, where responses may vary with each query.
Also Read: Salesforce Unveils MuleSoft Agent Fabric to Govern AI Agents
“GenAI is driving enterprise transformation, but it’s simultaneously creating new safety and security risks, that without safeguards, can erode customer trust, damage brand reputation, disrupt operations and expose companies to regulatory penalties,” said Bret Kinsella, General Manager, Fuel iX at TELUS Digital. “Red-teaming expertise is in short supply, and many organizations struggle to find the people and time needed to keep pace with evolving risks. Fuel iX Fortify helps close that gap by automating AI safety and security testing and uncovering vulnerabilities early so security teams can proactively mitigate risk. Importantly, it is accessible to non-technical users and backed by research. Fortify was built as an AI safety and security early warning system that is available to identify risks at any time by any user to give enterprises confidence they are responsibly launching and scaling their AI applications.”
Key Features of Fuel iX Fortify
-
Accessible Design: An intuitive interface enables both technical and non-technical teams to conduct AI security testing.
-
Actionable Reporting: Dashboards and detailed reports provide clear insights into each AI application’s vulnerabilities, enabling informed decisions to mitigate risks.
-
Seamless Integration: Compatible with a wide range of GenAI applications, all accessible from a single interface.
-
Advanced Attack Generation: Continuously updated to stay ahead of emerging threats, generating novel and repeatable adversarial tests.
Real-World Application in Healthcare
Fuel iX Fortify is actively deployed by a publicly-funded health authority in Canada to secure its public-facing career advisor chatbot. The AI bot assists individuals in exploring healthcare job opportunities, mimicking interactions with a recruiter while ensuring it never provides medical advice or harmful responses. With Fortify, the client achieved a 97% reduction in testing time, and onboarding non-technical staff took less than 30 minutes.
The client commented: “Fuel iX Fortify gave us confidence that our chatbot’s responses were safe, appropriate and met our standards. We found that manual red-teaming was slow, limited in scope and produced error rates as high as 13%. Fortify let us test our chatbot thoroughly before launch, so we knew it wouldn’t give harmful answers or fall short on compliance. With that assurance, we were able to launch responsibly, protect our reputation, and create a positive, human-like experience for people interested in healthcare careers.”
