Open-Weight AI Models Fail the Jailbreak Test

Cisco: One Prompt May Not Break Most AI Models, But a Conversation Will Rashmi Ramesh (rashmiramesh_) • February 23, 2026

Enterprise artificial intelligence deployments are running on models that fold nearly every time under sustained adversarial pressure, researchers have found.

See Also: How 72% of Enterprises Are Rewriting Cyber Resilience Playbooks

Cisco in its latest State of AI Security report tested eight open-weight large language models against multi-turn jailbreak attacks, which are sequences of iterative prompts designed to gradually steer a model into producing content its guardrails are meant to block. The attacks succeeded 92.78% of the time.

In single-turn tests, in which an attacker inputs a single prompt, success rates were considerably lower.

Open-weight models are AI systems whose underlying parameters are made publicly available, allowing developers to ...