37% of federal IT and cybersecurity decision makers list resilience against adversarial manipulation and prompt injection attacks as a top concern for agentic AI deployments
| Publisher | Booz Allen |
| Report | Velocity V5: Reimagining Cyber for a Faster Fight |
| Published | 21 July 2026 |
| Topics | Adversarial Attacks, AI Security, Federal agencies, Agentic AI |
Published by Booz Allen in Velocity V5: Reimagining Cyber for a Faster Fight, 21 July 2026. The figure is taken from the report as published; the full methodology is in the source.