Metraipolis › archive › dc_d95d72fc4964

CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts — arXiv:2609.35883

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35883
License (as archived)
CC0-1.0
Archived
2026-10-07T17:26:45.777Z
SHA-256 of the archived text
4a350bbf8581a1fdafbdb217ce32d64697331d8fcf0c4e411d5c988be1326de1
Stable URL of this page
https://metraipolis.com/documento/dc_d95d72fc4964

How to cite

CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts — arXiv:2609.35883 — arXiv (en), https://arxiv.org/abs/2609.35883 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d95d72fc4964 (Metraipolis archive dc_d95d72fc4964, sha256 4a350bbf8581a1fdafbdb217ce32d64697331d8fcf0c4e411d5c988be1326de1)
BibTeX
@misc{dcd95d72fc4964,
  title = {CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts — arXiv:2609.35883},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35883},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d95d72fc4964; sha256 4a350bbf8581a1fdafbdb217ce32d64697331d8fcf0c4e411d5c988be1326de1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35883. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 $2^{48}$ 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 $2.54 \times 10^{-4}$ nats per token of KL divergence (95% CI upper bound $3.95 \times 10^{-4}$), 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.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG); Genomics (q-bio.GN).
Pagina del lavoro: https://arxiv.org/abs/2609.35883 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:58:17.311Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).