arXiv (All)
open access
When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry
Mixture-of-Experts (MoE) language models produce routing information during inference that may be logged or exposed for monitoring, debugging, load analysis, and safety auditing. Unlike ordinary model outputs, this telemetry reveals a view of the model's internal computation, raising a privacy quest
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware#798975
- WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware#797561
- Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation#659133
- Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation#656997
- Individual costs and societal benefits: the privacy calculus of contact-tracing apps#404549
Record · ID 1247543
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive