# CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts

arXiv: https://arxiv.org/abs/2609.35883 · HTML: https://mlsanity.com/paper/2609.35883/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 28 of its 51 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)

## Builds on (most cited first, 28 of 28)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution](https://mlsanity.com/paper/2306.15794/) (2023)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware](https://mlsanity.com/paper/1806.03287/) (2018)
- [Petals: Collaborative Inference and Fine-tuning of Large Models](https://mlsanity.com/paper/2209.01188/) (2022)
- [MPCFormer: fast, performant and private Transformer inference with MPC](https://mlsanity.com/paper/2211.01452/) (2022)
- [THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption](https://mlsanity.com/paper/2206.00216/) (2022)
- [TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption](https://mlsanity.com/paper/2104.03152/) (2021)
- [PUMA: Secure Inference of LLaMA-7B in Five Minutes](https://mlsanity.com/paper/2307.12533/) (2023)
- [MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs](https://mlsanity.com/paper/2508.15036/) (2025)
- [Stealing User Prompts from Mixture of Experts](https://mlsanity.com/paper/2410.22884/) (2024)
- [Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption](https://mlsanity.com/paper/2505.07329/) (2025)
- [Expert Selections In MoE Models Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2602.04105/) (2026)
- [CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing](https://mlsanity.com/paper/2511.01197/) (2025)
- [SecMoE: Communication-Efficient Secure MoE Inference via Select-Then-Compute](https://mlsanity.com/paper/2601.06790/) (2026)
- [How Private Are DNA Embeddings? Inverting Foundation Model Representations of Genomic Sequences](https://mlsanity.com/paper/2603.06950/) (2026)
- [Quantifying Memorization and Privacy Risks in Genomic Language Models](https://mlsanity.com/paper/2603.08913/) (2026)
- [Feasibility of Homomorphic Inference for a Genomic Foundation Model](https://mlsanity.com/paper/2609.16211/) (2026)

## Abstract (arXiv)

Genome foundation models are growing into sparse mixture-of-experts (MoE) networks whose expert weights no longer fit on the machines that hold the sequences, yet sending a private genome to rented accelerators exposes it: we show that a single server hosting one expert recovers the input nucleotides with 99.8% top-1 accuracy. We present CipherGenome, a protocol that keeps the embedding, attention and router of a 15.1B-parameter MoE genome model on a trusted thin client and outsources every expert projection, 95.8% of the parameters, to untrusted and possibly colluding GPU servers under module-LWE encryption. The design exploits three structural facts: expert layers are linear between two SwiGLU gates, expert weights are public, and GPU integer tensor cores can evaluate a ciphertext-weight product exactly modulo 248 in a single GEMM. The client evaluates the nonlinearity exactly and re-encrypts with fresh secrets, so no polynomial approximation or bootstrapping is ever needed. On 72 windows from 12 bacterial genomes, encryption adds 2.54 × 10-4 nats per token of KL divergence (95% CI upper bound 3.95 × 10-4), below a pre-registered non-inferiority margin and indistinguishable from bf16 inference, while the same inversion attack falls to chance level. A reusable public hint cuts end-to-end latency by 3.54 times, wire compression reduces traffic 6.8 times, per-layer padding reduces routing leakage from 54.9% to 8.9% accuracy, and HE-compatible int4 experts remain non-inferior to their plaintext counterparts. Per expert and token, the server-side cost is more than six orders of magnitude below a CKKS baseline.