Cerbere-AG – The layer that ensures security, observability and control, which sits between the AI agent and the real world

说明与用途

Cerbere-AG 通过 Regex、ML 和 LLM Judge 三层安全防护，为自主 AI 代理提供安全、可观测性和控制，降低攻击成功率并提供审计跟踪。

问题

AI agents act autonomously and can perform unintended or malicious actions, requiring guardrails that balance autonomy with control.

结果

Cerbere-AG reduces attack success to below 30% with Regex, achieves 100% recall with ML, and resolves ambiguous cases with an LLM Judge, while providing an audit trail for compliance.

工作流

• 1. Agent issues a tool call.
• 2. Regex layer filters obvious malicious patterns.
• 3. ML layer classifies remaining calls, raising recall to 100% in tests but flagging uncertain cases.
• 4. LLM Judge evaluates ambiguous cases, considers context, and decides to allow, block, or flag for human approval.
• 5. Collector records spans and traces into an audit trail independent of the agent.

证据

Regex alone lets more than 30% of attacks through.

来源

ML pushes recall up to 100% in some of our tests, but raises false positives.

来源

The LLM Judge resolves the ambiguous cases ML can’t classify.

来源