TL++ recovers centralized mini-batch gradients via virtual batches in split learning and adds secret sharing for cut-layer tensors, achieving 91.41% accuracy on CIFAR-10 with 13x lower communication than full-model sync.
CURE: Privacy-Preserving Split Learning Done Right
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Training deep neural networks often requires large-scale datasets, necessitating storage and processing on cloud servers due to computational constraints. The procedures must follow strict privacy regulations in domains like healthcare. Split Learning (SL), a framework that divides model layers between client(s) and server(s), is widely adopted for distributed model training. While Split Learning reduces privacy risks by limiting server access to the full parameter set, previous research has identified that intermediate outputs exchanged between server and client can compromise client's data privacy. Homomorphic encryption (HE)-based solutions exist for this scenario but often impose prohibitive computational burdens. To address these challenges, we propose CURE, a novel system based on HE, that encrypts only the server side of the model and optionally the data. CURE enables secure SL while substantially improving communication and parallelization through advanced packing techniques. We propose two packing schemes that consume one HE level for one-layer networks and generalize our solutions to n-layer neural networks. We demonstrate that CURE can achieve similar accuracy to plaintext SL while being 16x more efficient in terms of the runtime compared to the state-of-the-art privacy-preserving alternatives.
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A survey that introduces a unified training pipeline and taxonomizes split learning approaches for LLM fine-tuning across model, system, and privacy dimensions.
citing papers explorer
-
TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systems
TL++ recovers centralized mini-batch gradients via virtual batches in split learning and adds secret sharing for cut-layer tensors, achieving 91.41% accuracy on CIFAR-10 with 13x lower communication than full-model sync.
-
A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations
A survey that introduces a unified training pipeline and taxonomizes split learning approaches for LLM fine-tuning across model, system, and privacy dimensions.