Back to AI News
Ars Technica AI

Canary experiment exposes sensitive-data leaks across AI routing supply chain

Researcher HD Moore planted 2 million digital canaries in prompts routed through a sprawling network of AI services to trace how sensitive information leaks. The canaries included unused AWS keys, SSH passwords, unique URLs, DNS names, and private git repository references, each seeded into exactly one prompt sent to a single provider. The experiment found that the AI supply chain leaked highly sensitive data extensively, highlighting privacy and security risks in AI routers and gateways that broker prompts to inference providers.

AI Brief

It reveals concrete privacy and security risks in the increasingly common AI router/gateway layer that developers use to route prompts across model providers.

Researchers planted 2 million digital tripwires in requests sent through a sprawling network of AI services to find out what happened to sensitive information entrusted to them. What they discovered was an ecosystem that leaked highly sensitive data like a sieve.

The exposure was found through an ingenious experiment designed to test if sensitive information can leak through the vast chain of widely used AI services and how that information is exploited when it does. Many of today’s AI apps use services such as OpenRouter or Vercel that act as brokers. These “AI routers,” sometimes also known as “AI gateways,” receive large numbers of prompts sent from AI app end users and route them to an available inference engine based on criteria such as the one charging the lowest price or being best suited for the given task. Instead of using Anthropic, OpenAI, or another big provider, the developer hires an AI router to find the most suitable model.

Security breaches, prompt theft, and privacy violations

To test for potential leakage, researcher HD Moore assembled a collection of AWS access keys, functioning credentials tied to empty AWS accounts, passwords for services such as SSH, and unique URLs, DNS names, and private git repository references. None of the secrets had ever been used before, and he controlled the infrastructure that received any requests using the credentials. He then seeded each secret into exactly one prompt sent to a single provider. In the event any of the secrets were leaked, these “canaries”—so called because they resemble the role of that bird when taken into coal mines—would allow Moore to identify each link in the chain that was responsible.

Read full article

Comments

ai-privacy-leakage-1152x648.jpg
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!