Tag

inference

2 entries.

1. 9 Oct

   A cache hit is not a trust grant

   LLM serving caches the prefix and the answer, not the decision about them. What one tenant writes into the shared cache, another inherits — and the latency tells your adversary what you cached.

   • Red Team
   • ai-security
   • inference
   • multi-tenant
   • side-channel
   • prompt-injection
2. 31 Aug

   Loopback is not a trust boundary

   Binding an unauthenticated model API to every interface is not loopback. The sandbox can still hold while the agent is owned.

   • inference
   • network
   • sandbox