aggregate inference traffic in the paper's model-exfiltration threat-model example—not output from one production inference server

Name: aggregate inference traffic in the paper's model-exfiltration threat-model example—not output from one production inference server
License: https://aidatacenterguide.com/terms#intellectual-property

~125 GB/day aggregate assumed trafficmodeled

Value kind	modeled — Interpret this value according to its displayed kind, scope, source, and as-of date.
Scope	Aggregate traffic assumption in the cited threat-model example; not observed output from one server and not a recommended export budget.
As of	2026-03-12
Source	Rinberg et al., “Verifying LLM Inference to Detect Model Weight Exfiltration,” arXiv:2511.02620v3, 12 March 2026; modeled aggregate output assumption, not measured per-server throughput. · Introduction and Contributions, traffic-volume example
Review	checking…review by 2026-09-27 · fast cadence
Recorded changes	last 2026-09-16 · 3 revisions tracked
Claim id	token-output-of-a-single-production-inference

Where the guide uses it

11.8 Model & Weight Protection (At-Rest, In-Transit, In-Use)

← Full numbers register — every date-stamped figure in the guide, with revision history.