Multi-turn attacks broke AI models 88% of the time — single-turn testing missed it, Cisco AI security lead warns at VB Transform 2026
AI Summary
Cisco's analysis found that multi-turn attacks successfully compromised AI models 88.3% of the time, highlighting the inadequacy of single-turn testing methods. This alarming result was presented by Amy Chang during the VB Transform 2026 conference, emphasizing the need for improved security measures in AI systems.
From the source
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 explains why the room was full. More than half, 5
The full text couldn't be loaded here (the source may require a subscription).
View original at VentureBeat AI