# Mixture-of-experts routing safety

Area: [LLM safety and security](https://mlsanity.com/safety/index.md). HTML: https://mlsanity.com/safety/mixture-of-experts-routing-safety/

## Key facts

- Mixture-of-experts routing safety: 20 papers on arXiv since 2025 (data through 14 Oct 2026).
- 9 of its 20 mapped papers (45%) cite “BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts” (2025, arXiv 2504.18598).
- 9 of its 20 mapped papers (45%) cite “SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification” (2025, arXiv 2506.17368).
- 1 new papers 24 Sep–14 Oct.

## Most cited here

- [BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts](https://mlsanity.com/paper/2504.18598/) (2025), cited by 9 papers here
- [SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification](https://mlsanity.com/paper/2506.17368/) (2025), cited by 9 papers here
- [Steering MoE LLMs via Expert (De)Activation](https://mlsanity.com/paper/2509.09660/) (2025), cited by 8 papers here
- [GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs](https://mlsanity.com/paper/2512.21008/) (2025), cited by 4 papers here
- [Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs](https://mlsanity.com/paper/2602.08621/) (2026), cited by 3 papers here
- [Life-Cycle Routing Vulnerabilities of LLM Router](https://mlsanity.com/paper/2503.08704/) (2025), cited by 2 papers here
- [Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing](https://mlsanity.com/paper/2602.08741/) (2026), cited by 2 papers here
- [How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities](https://mlsanity.com/paper/2504.07113/) (2025), cited by 1 papers here
- [RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models](https://mlsanity.com/paper/2602.04448/) (2026), cited by 1 papers here
- [Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization](https://mlsanity.com/paper/2604.15022/) (2026), cited by 1 papers here

## New (24 Sep–14 Oct)

- [When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry](https://mlsanity.com/paper/2610.10616/) (2026-10-07)