# Multi-turn attacks breached AI models 88% of the time Cisco security expert reveals inadequacy of single-turn testing methods. - **Source:** [VentureBeat (feeds.feedburner.com)](https://brifing.si/source/c51474dc-6b09-49dd-aaca-085f4ed00c84) - **Published:** 2026-07-23 - **Topic:** [Data & AI](https://brifing.si/c/data-ai) - **Original article:** - **On Brifing:** https://brifing.si/s/3da10a92-b4a8-4c04-8aab-188b34356b0b ## Staggering success rate of multi-turn attacks Cisco's research on 15 leading AI models showed multi-turn attacks achieving up to 88.3% success rate, exposing the limitations of traditional single-turn testing in evaluating AI security robustness. ## Industry-wide security gap Enterprise surveys reveal 54% of companies have already experienced an AI security incident, yet only 30% isolate high-risk agents in sandboxes. This indicates a critical protection gap across the sector. ## Major security acquisitions Billion-dollar purchases by Palo Alto Networks, CrowdStrike and Cisco reflect growing AI security concerns. Investments in identity management and isolation layers are particularly noteworthy. ## Expert perspective from Amy Chang With 20 years in cybersecurity, Chang emphasizes how single-turn tests fail to capture real-world interactions. She demonstrates how extended dialogues better reveal model vulnerabilities. ## Comprehensive research methodology The study involving 30,090 single-turn and 6,986 multi-turn attacks showed models ranked differently by test type, highlighting the critical importance of methodology selection in security evaluations. ## Importance of realistic testing Chang explains how multi-turn attacks better reflect actual usage scenarios than one-off malicious prompts, uncovering vulnerabilities that snapshot testing misses completely. ## Cisco's proactive solution The Integrated AI Security Framework addresses risks across the entire lifecycle from supply chain to models. Teams can develop comprehensive strategies based on real incident analysis. ## Box's three-layer defense Box CISO Ceylan shared their permission management, ephemeral sandboxes and runtime restrictions strategy that fundamentally prevents unauthorized agent actions. ## Fragility of trust building Box's experience showed how one mistake can erase months of accumulated trust. Ceylan emphasized the critical need for continuous monitoring and human oversight. ## Wake-up call for the industry Experts advocate returning to security fundamentals. Multi-turn testing, layered defenses and continuous monitoring prove vital in preventing model misuse. ## Sources covering this story - https://venturebeat.com/security/openai-anthropic-google-and-xai-models-all-broke-under-multi-turn-attack-up-to-88-of-the-time — --- _Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._