F5 introduces enhanced threat intelligence resources through its F5 Labs team, establishing industry-leading benchmarks for AI model security with the Comprehensive AI Security Index (CASI) and Agentic Resistance Score (ARS) leaderboards. These monthly-updated rankings help organizations evaluate and compare the risk profiles of popular AI models before deployment.
F5, a global leader in application delivery and security, expands its AI security offerings via F5 Labs following the acquisition of CalypsoAI. The new leaderboards deliver consistent, data-driven metrics to assess how well leading AI models withstand evolving threats, empowering security teams to make informed decisions on model selection and governance.
As AI integrates into critical business operations, validating model security has become essential. F5 Labs addresses this by providing objective rankings that go beyond basic performance to measure paths of least resistance and minimum resources needed for successful attacks.
The Comprehensive AI Security Index (CASI) ranks models on:
The Agentic Resistance Score (ARS) focuses on real-world endurance against prolonged, adaptive attacks by AI agents. It assesses:
These metrics stem from extensive red-teaming data and continuous threat monitoring, offering enterprises a reliable way to compare models and providers.
“Deploying unverified AI models into critical infrastructure is not innovation; it is negligence. Organizations need a way to continuously quantify resilience. F5 Labs AI Leaderboards offer that standard. These rankings isolate specific weaknesses in the model layer, giving security teams the intelligence they need to govern inference and block attacks before they happen,” said Kunal Anand, Chief Product Officer at F5.
The leaderboards integrate with F5’s broader platform, including F5 AI Guardrails for applying custom and out-of-the-box protections, and F5 AI Red Team for rigorous, autonomous testing that simulates evolving threats. Together, these capabilities help organizations secure APIs, protect data, prevent DDoS, and accelerate DevSecOps.
F5 Labs also publishes monthly AI Security Insights articles analyzing leaderboard movements, emerging threats, and deep dives into specific attack techniques.
“F5’s existing traffic inspection and logging capabilities are expanded with the acquisition of CalypsoAI, adding runtime AI governance capabilities and visibility into AI system behavior. Paired with their security research arm, F5 Labs, that updates CASI and ARS rankings every month, F5 customers are provided with both a useful set of security metrics to consider when selecting an AI model, as well as the tools needed to constrain how AI systems are used, what data they may access, and how outputs are generated,” said Grace Trinidad, Research Director, AI Security & Trust, IDC.
By formalizing transparent benchmarks, F5 Labs advances collective knowledge sharing and encourages stronger application security practices across the industry.
About F5
F5, Inc. is the global leader that delivers and secures every app. Backed by three decades of expertise, F5 has built the industry’s premier platform—F5 Application Delivery and Security Platform (ADSP)—to deliver and secure every app, every API, anywhere: on-premises, in the cloud, at the edge, and across hybrid, multicloud environments. F5 is committed to innovating and partnering with the world’s largest and most advanced organizations to deliver fast, available, and secure digital experiences. Together, we help each other thrive and bring a better digital world to life.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.