HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation

arXiv:2609.01730 · cs.CR, cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-01

Updated: 2026-09-30

Code: https://github.com/gladia-research-group/heat

Terminology

• Transformer — 16× in this paper · explained in 2 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Calibration — 8× in this paper · explained in 7 episodes
• Decode — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• KV cache — 2× in this paper · explained in 3 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Activation Function — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fully Homomorphic Encryption (FHE) — 1× in this paper · explained in 5 episodes
• Homomorphic Encryption-Aware Training — 1× in this paper
• Quantization-Aware Training — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• PonderNet: Learning to Ponder
• Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption
• Peregrine: One-Shot Fine-Tuning for FHE Inference of General Deep CNNs
• Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache
• Power-Softmax: Towards Secure LLM Inference over Encrypted Data

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs