# Researchers Show Encrypted Cloud LLM Traffic Reveals the Model, the Prompt Category and the Agent Task

A new public benchmark covers 60,000 user interactions across 10 models and 2,838 multi-agent runs, inferring behaviour from packet sizes and timing alone.

- Published: 2026-09-29T06:12:03.689Z
- Canonical: https://polylog.news/ai/2026-09-29/researchers-show-encrypted-cloud-llm-traffic-reveals-the-mod
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CR](https://arxiv.org/abs/2609.31877)

A team from Chalmers University of Technology, the University of Texas at El Paso, Old Dominion University and George Mason University has published the first unified measurement study of what an eavesdropper can learn from encrypted traffi…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-29/researchers-show-encrypted-cloud-llm-traffic-reveals-the-mod (subscription information: https://polylog.news/pricing).