CrowdStrike expands Falcon with security for AI interactions

"According to CrowdStrike, part of the security threat is shifting from traditional infrastructure to the way organizations apply generative AI. Where existing security solutions focus primarily on data, models, and infrastructure, Falcon AIDR emphasizes the interaction between users, applications, and AI models. This interaction layer is becoming increasingly important as generative AI is used more widely within organizations, both during software development and by employees in their daily work."

"According to analysis by SiliconANGLE, CrowdStrike applies the same architectural principles to AIDR as it did previously to endpoint detection and response (EDR). Instead of introducing separate security measures, AI security is integrated into a single platform that continuously collects and correlates telemetry. CrowdStrike thus positions the AI interaction layer as a fully-fledged part of the broader security domain, comparable to endpoints, cloud workloads, and identities."

"Attacks on this layer include prompt injection, in which hidden instructions are added to input to cause AI systems to exhibit undesirable behavior. This can lead to the circumvention of security measures, the manipulation of output, or the exposure of sensitive information. In addition, the solution offers options for blocking AI interactions in real time when they are deemed risky. This includes detecting and stopping prompt injection attacks,"

Falcon AIDR targets the AI interaction layer where prompts, agents, and responses create a new attack surface. The security threat is shifting from traditional infrastructure to the ways organizations apply generative AI. Existing solutions often focus on data, models, and infrastructure, while Falcon AIDR emphasizes interactions among users, applications, and AI models. Attacks such as prompt injection can cause undesirable behavior, expose sensitive information, or bypass controls. The solution integrates AI security into a single platform that continuously collects and correlates telemetry, records runtime logs for compliance and investigation, and can block risky AI interactions in real time.

Read at Techzine Global