CipherGenome is presented, 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.
Abstract
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.
The biomedical significance is that, under the stated threat model, a served genomic model can process an encoded sequence without exposing plaintext queryderived activations to the compute provider.
C. Galanopoulos, K. Provatas, I. Georgakopoulos-Soares· arXiv.org· 1 citation
Genome foundation models are most useful where sequences are generated, yet the largest models need datacenter accelerators and a place to send private DNA. We ask whether a 15-billion-parameter genome mixture-of-experts (MoE) model can instead run on volunteers'web browsers, with the experts spread across many untrust...
Two solutions for serving one open-weight language model to many tenants. TEMPLE-KEY-TRUST-HOST. Every tenant speaks to the model in its own secret private language: a per-tenant key 𝜅=(𝜋,𝑄)—a homophonic permutation 𝜋 of the vocabulary and a secret orthogonal rotation 𝑄 of the residual stream. A pretrained transformer...
Patil Milind K· International Journal of Sci...· 0 citations
Large Language Models (LLMs) have made it exceptionally convenient for users to send their private data to model providers, which process them in plaintext. Fully Homomorphic Encryption (FHE) promises to secure remote inference by computing directly on encrypted data, yet it has remained prohibitively slow. The effort...
Alessandro Zirilli, Davide Marincione, E. Kornaropoulos et al.· 0 citations
This paper presents a framework that automatically converts a pre-trained Keras model into a CKKS equivalent, handling parameter inference, bootstrap placement and encrypted execution without retraining, with the user only providing a configuration of the encryption parameters.
Dennis van der Werff, Georgios Tasopoulos, Francesco Regazzoni· Proceedings of the 14th Work...· 0 citations
Leveraging this reduction yields a non-interactive protocol for encrypted federated training of hybrid quantum--classical networks, which includes correctness proofs for aggregation and sign handling, plus a compilation lemma proving parameterised entanglers add only constant-factor overhead without altering the depth...
Marcel Mordarski, N. Mani, Arshad Patel et al.· 0 citations
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.