VelkiroVELKIRO

Effective against

  • Claude Opus 4.6
  • Claude Opus 4.7
  • Claude Opus 4.8
  • Claude Opus 5.0
  • Claude Sonnet 5.0
  • DeepSeek 4.1 Flash
  • DeepSeek V4 Pro
  • Gemini 3.1 Pro
  • Gemini 3.8 Flash
  • GLM 5.1
  • GLM 5.2
  • GLM 5.3
  • GLM 5.3 Flash
  • GPT-5.5
  • GPT-5.6
  • GPT-5.6 Luna
  • GPT-5.6 Terra
  • GPT-5.6 Sol
  • GPT-6 Astra
  • Grok 4.5
  • Grok 4.6
  • Kimi K3
  • Llama 3.2
  • Muse Spark 1.1
  • Muse Spark 1.2
  • Muse Spark 1.3
  • Qwen 3.8 Max

Solutions

The ABC² of Deception

What we deploy, and what it does

AI Manipulation technology

AIM is a novel defensive technology built to influence the decisions made by AI-enabled threats inside a compromised environment.

AIM artefacts blend into the systems and data an attacker would normally examine. When an AI agent encounters them, they can redirect its activity away from genuine assets and towards controlled outcomes. This can interrupt an attack, slow its progress, trigger a high-confidence detection or capture useful information for responders.

What AIM exploits

AIM targets multiple fundamental characteristics and weaknesses of AI systems, rather than a vulnerability in a particular model. We'd be happy to discuss the specifics of this with you, and if you would like to know more please contact us or request a demo.

Each AIM deployment is tailored to the customer's environment and monitored to ensure the artefacts remain present and current. AIM does not require additional infrastructure within the customer's network to deploy, and we actively test your artefacts against every new frontier AI model available. We are constantly testing and improving our AIM artefacts, and when a new one is required, we will let you know and provide it through your customer console.

Cassowaries

Our cassowaries are canaries that are levelled up in breadth, simplicity, and ruthless efficiency. With 170 types available, we help you select the most effective ones for your environment, without requiring any additional log source ingestion for detection.

Our cassowaries grant zero real privilege, hold zero real data, and fire an alert when it is used to perform attempted authentication. An alert is a near-zero-false-positive breach signal of an AI-enabled or human threat, enabling you to kill two threats with one bird.

Console

Each deployment comes with your own customer console. From here you can easily download and implement the deception artefacts, monitor to ensure your protection is current, and read about the latest threat intelligence and testing research from our team.

Kill two threats with one bird

Book a demo today

A walkthrough of how it works, the research behind AIM Technology, and how it can protect your business from human and AI-enabled threats.