ReBoot: Encrypted Training of Deep Neural Networks with CKKS Bootstrapping

arXiv:2506.19693 · cs.LG · Submitted 2025-06-24 · Read on arXiv

cs.LG

Submitted: 2025-06-24

Updated: 2025-06-24

Journal ref: Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24837-24845 (2026)

DOI: 10.1609/aaai.v40i29.39670

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Homomorphic Encryption — 28× in this paper
• Accuracy — 26× in this paper · explained in 1 episode
• Activation Function — 11× in this paper · explained in 1 episode
• Loss Function — 11× in this paper · explained in 2 episodes
• Machine Learning — 11× in this paper
• Fully Homomorphic Encryption — 10× in this paper
• Computational overhead — 8× in this paper · explained in 2 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Deep Learning — 5× in this paper
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Transfer Learning — 4× in this paper · explained in 10 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Homomorphic Encryption Standard — 2× in this paper
• Alignment — 1× in this paper · explained in 1 episode
• Alternation — 1× in this paper · explained in 1 episode
• Communication Overhead — 1× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition Workshops — 1× in this paper
• Differential Privacy — 1× in this paper · explained in 4 episodes
• Fully Homomorphic Encryption (FHE) — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hybrid Approach — 1× in this paper · explained in 4 episodes
• Nesterov Accelerated Gradient — 1× in this paper
• Quantization — 1× in this paper · explained in 12 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Ring Learning With Errors — 1× in this paper
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Deep Learning using Rectified Linear Units (ReLU)
• On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks
• Neural Network Training With Homomorphic Encryption
• Neural Network Training on Encrypted Data with TFHE
• Training Neural Networks with Local Error Signals
• I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
• Local Learning with Neuron Groups
• NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks
• CryptoTL: Private, Efficient and Secure Transfer Learning
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks