Multi-turn attacks broke AI models 88% of the time — single-turn testing missed it, Cisco AI security lead warns at VB Transform 2026

Jeetu Patel, Cisco President: Fortt Knox Innovation Lab

At AMD's Advancing AI event, Cisco product chief Jeetu Patel argues inferencing is shifting from spiky chatbots to always-on agents, driving "deskside" devices that run hundreds of agents beside your laptop. He casts Cisco as the common security/management plane across cloud, private, and local AI, backs open source (new 350M/1B vuln-finding models), and says cheaper tokens boost demand via Jevons Paradox — optimize cost-per-outcome, not per-tok…

Multi-turn attacks broke AI models 88% of the time — single-turn testing missed it, Cisco AI security lead warns at VB Transform 2026

When Cisco ran 6,986 multi-turn attacks against 15 flagship models, attackers who adapted across the conversation broke through as often as 88.3% of the time. Amy Chang, Cisco's head of AI threat intelligence and security research, brought that finding to the agentic security panel at VB Transform 2026; the number should worry anyone still running single-turn red-teaming programs.VentureBeat's June 2026 Pulse survey of 107 enterprise respondents…