# When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry

arXiv: https://arxiv.org/abs/2610.10616 · HTML: https://mlsanity.com/paper/2610.10616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)
- LLM safety and security / [Mixture-of-experts routing safety](https://mlsanity.com/safety/mixture-of-experts-routing-safety/)

## Builds on (most cited first, 11 of 11)

- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Do Membership Inference Attacks Work on Large Language Models?](https://mlsanity.com/paper/2402.07841/) (2024)
- [LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training](https://mlsanity.com/paper/2411.15708/) (2024)
- [Stealing User Prompts from Mixture of Experts](https://mlsanity.com/paper/2410.22884/) (2024)
- [Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens](https://mlsanity.com/paper/2407.21248/) (2024)
- [Window-based Membership Inference Attacks Against Fine-tuned Large Language Models](https://mlsanity.com/paper/2601.02751/) (2026)
- [Expert Selections In MoE Models Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2602.04105/) (2026)
- [AttenMIA: LLM Membership Inference Attack through Attention Signals](https://mlsanity.com/paper/2601.18110/) (2026)
- [Task-Conditioned Routing Signatures in Sparse Mixture-of-Experts Transformers](https://mlsanity.com/paper/2603.11114/) (2026)
- [RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry](https://mlsanity.com/paper/2605.24817/) (2026)
- [Learning the Signature of Memorization in Autoregressive Language Models](https://mlsanity.com/paper/2604.03199/) (2026)

## Abstract (arXiv)

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 question: can it reveal whether an example was used to fine-tune the deployed model? We introduce a router-augmented membership inference attack that combines conventional output-side signals with aggregated routing features and applies a membership classifier learned from independently fine-tuned shadow models to the target model. Across three MoE architectures and three data domains, router telemetry consistently improves membership inference over a strong output-signal ensemble, increasing TPR at 1% FPR by 2.7--9.4 percentage points across all nine settings. The leakage persists across full fine-tuning, frozen-router training, LoRA, and instruction tuning, and remains observable with only discrete expert selections, restricted telemetry, or a single shadow model. Mechanistic analysis further shows that the leakage does not require router-specific memorization: fine-tuning introduces membership information into hidden representations, while the router exposes a projection of this signal even when its parameters are frozen. Perturbing the telemetry reduces this additional leakage only as its fidelity degrades. Our results show that router telemetry can turn an operational signal into an additional privacy surface for fine-tuned MoE models.