# Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs

arXiv: https://arxiv.org/abs/2605.04446 · HTML: https://mlsanity.com/paper/2605.04446/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Mixture-of-experts routing safety, one of 12 directions in LLM safety and security.
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 6 May 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2404.03027/) (2024)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic](https://mlsanity.com/paper/2402.11746/) (2024)
- [Steering MoE LLMs via Expert (De)Activation](https://mlsanity.com/paper/2509.09660/) (2025)
- [Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks](https://mlsanity.com/paper/2407.00869/) (2024)
- [TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts](https://mlsanity.com/paper/2506.07596/) (2025)
- [SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification](https://mlsanity.com/paper/2506.17368/) (2025)
- [Teacher Model Fingerprinting Attacks Against Transfer Learning](https://mlsanity.com/paper/2106.12478/) (2021)
- [BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts](https://mlsanity.com/paper/2504.18598/) (2025)
- [Buffer Overflow in Mixture of Experts](https://mlsanity.com/paper/2402.05526/) (2024)
- [Stealing User Prompts from Mixture of Experts](https://mlsanity.com/paper/2410.22884/) (2024)
- [GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs](https://mlsanity.com/paper/2512.21008/) (2025)
- [Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs](https://mlsanity.com/paper/2602.08621/) (2026)
- [Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization](https://mlsanity.com/paper/2604.15022/) (2026)

## Built on by (most cited first, 3 of 3)

- [RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry](https://mlsanity.com/paper/2605.24817/) (2026)
- [BadEngram: Backdoor Attack on Gated Memory Components in LLMs](https://mlsanity.com/paper/2609.13478/) (2026)
- [Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM](https://mlsanity.com/paper/2610.02910/) (2026)

## Abstract (arXiv)

Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduces a new attack surface: the routing mechanism that determines which experts process each input. Prior work shows that manipulating routing can bypass safety alignment, but existing attacks require model modification and thus apply only to locally deployed models. By contrast, real-world LLM services are remotely hosted and accessible only through input queries. This raises a fundamental question: can MoE routing be exploited through input-only attacks to induce stronger unsafe behaviors in real-world services? Our key insight is to optimize attacks in a white-box setting on open-source surrogate MoE models and transfer the resulting adversarial inputs to public API services within the same model family. This setting presents three main challenges: routing can be influenced only indirectly through input perturbations, routing control and output generation are tightly coupled, and even a successful safety bypass may still produce low-quality responses. To address these challenges, we propose Misrouter, an input-only attack framework that jointly targets routing behavior and expert functionality. Misrouter identifies weakly aligned experts that are willing to produce target harmful content by analyzing expert activations under harmful queries paired with unsafe continuations. It then optimizes adversarial inputs to steer routing toward these experts and away from strongly aligned ones. It further biases routing toward highly capable general-purpose experts identified from benign question-answering tasks. Finally, because routing and output objectives can conflict, Misrouter uses a two-phase optimization strategy that first steers routing and then optimizes harmful outputs while preserving routing stability.