Perseus: A Full-Stack System for Homomorphic Model Inference
cs.CR, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/qlabs-eng/noise
Terminology
Sources
- Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache
- Static Bootstrap Placement for Encrypted Language Model Decoding
- ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation
- Scaling up FHE-based Privacy-Preserving ML: Higher Throughput, Longer Inputs for LLama-3-8B
- HEAAN Demystified: Accelerating Fully Homomorphic Encryption Through Architecture-centric Analysis and Optimization
- Power-Softmax: Towards Secure LLM Inference over Encrypted Data
- Efficient Decoding Methods for Language Models on Encrypted Data
- Fiona: Accelerating FHE Inference with Packing-Aware Ternary Weights
- HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
- An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference
- Cerium: A Multi-GPU Framework for Terabyte-Scale Encrypted Inference
- ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data