EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE

• URL: http://arxiv.org/abs/2609.13636v1
• Date: Sat, 12 Sep 2026 01:00:19 GMT
• Title: EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE
• Abstract summary: We present EI-DDLGN, the first in-depth study of TFHE-based DDLGN inference.<n>We also introduce Model-Fixed-Wire PBS Bypass, a semantics-preserving execution strategy.<n> Evaluations across 72 depth-width configurations on MNIST, FashionMNIST, and UCI Phishing show that DDLGNs constitute an efficient alternative to arithmetic TFHE inference.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Privacy-preserving inference via Torus Fully Homomorphic Encryption (TFHE) provides strong protection for sensitive data in outsourced deep learning applications. However, most TFHE-compatible neural network frameworks remain based on arithmetic neural architectures, resulting in high inference latency due to programmable bootstrapping (PBS), accumulator growth, and circuit bit-width sensitivity. In this work, we investigate Deep Differentiable Logic Gate Networks (DDLGNs) as a Boolean-native alternative for encrypted inference under TFHE. Because DDLGNs learn Boolean computations directly and discretize into fixed logic gate networks, their inference procedure is naturally aligned with TFHE's Boolean execution model and avoids arithmetic accumulation in hidden layers. We present EI-DDLGN, the first in-depth study of TFHE-based DDLGN inference, and characterize how encrypted execution cost depends on model size, learned Boolean-function distribution, and propagated wire status. We also introduce Model-Fixed-Wire PBS Bypass (MFW-PBS Bypass), a semantics-preserving execution strategy that eliminates unnecessary PBS operations without modifying the learned network topology. Evaluations across 72 depth-width configurations on MNIST, FashionMNIST, and UCI Phishing show that DDLGNs constitute an efficient alternative to arithmetic TFHE inference, achieving substantially improved accuracy-latency trade-offs. Notably, on MNIST, EI-DDLGN-Small matches the accuracy of QAT-FCNN-4 while reducing encrypted inference latency by 13.4x. Our implementation is available at https://github.com/Carleton-SCI/EI-DDLGN

Related papers

• On the Depth Scalability of Logic Gate Networks [8.615180964202992]
  We introduce Input-Anchored Logic Gate Networks (IALGNs)<n>We show that IALGNs achieve consistent fixed-width depth--accuracy improvements beyond 100 layers.<n>These results demonstrate that scalable depth in LGNs requires both stable optimization and an information-access pattern.
  arXiv  Detail & Related papers  (2026-07-19T20:11:53Z)
• TorchLean: Formalizing Neural Networks in Lean [71.68907600404513]
  We introduce TorchLean, a framework that treats learned models as first-class mathematical objects with a single, precise semantics shared by execution and verification.<n>We validate TorchLean end-to-end on certified robustness, physics-informed residual bounds for PINNs, and Lyapunov-style neural controller verification.
  arXiv  Detail & Related papers  (2026-02-26T05:11:44Z)
• Causal Autoregressive Diffusion Language Model [70.7353007255797]
  CARD reformulates the diffusion process within a strictly causal attention mask, enabling dense, per-token supervision in a single forward pass.<n>Our results demonstrate that CARD achieves ARM-level data efficiency while unlocking the latency benefits of parallel generation.
  arXiv  Detail & Related papers  (2026-01-29T17:38:29Z)
• Efficient and Encrypted Inference using Binarized Neural Networks within In-Memory Computing Architectures [2.5756681494057045]
  Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources.<n>Recent studies highlight the potential of mapping BNN model parameters onto emerging non-volatile memory technologies.<n>However, protecting model parameters from theft attacks by storing them in an encrypted format and decrypting them at runtime introduces significant computational overhead.
  arXiv  Detail & Related papers  (2025-10-27T05:59:02Z)
• DESIGN: Encrypted GNN Inference via Server-Side Input Graph Pruning [21.652233892742366]
  DESIGN (EncrypteD GNN Inference via sErver-Side Input Graph pruNing) is a novel framework for efficient encrypted GNN inference.<n>Our framework achieves significant performance gains through a hierarchical optimization strategy executed entirely on the server.
  arXiv  Detail & Related papers  (2025-07-08T04:01:53Z)
• DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment [57.62885438406724]
  Graph neural networks are recognized for their strong performance across various applications. BP has limitations that challenge its biological plausibility and affect the efficiency, scalability and parallelism of training neural networks for graph-based tasks. We propose DFA-GNN, a novel forward learning framework tailored for GNNs with a case study of semi-supervised learning.
  arXiv  Detail & Related papers  (2024-06-04T07:24:51Z)
• FOBNN: Fast Oblivious Inference via Binarized Neural Networks [13.635520737380103]
  We propose FOBNN, a Fast Oblivious inference framework via Binarized Neural Networks.<n>We develop the Bit Length Bounding (BLB) algorithm, which minimizes bit representation to decrease redundant computations.<n>We also enhance the binarized neural network structure through link optimization and structure exploration.
  arXiv  Detail & Related papers  (2024-05-06T03:12:36Z)
• Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach [64.23331120621118]
  This paper proposes a theoretical and computational framework for training and robustness verification of implicit neural networks. We introduce a related embedded network and show that the embedded network can be used to provide an $ell_infty$-norm box over-approximation of the reachable sets of the original network. We apply our algorithms to train implicit neural networks on the MNIST dataset and compare the robustness of our models with the models trained via existing approaches in the literature.
  arXiv  Detail & Related papers  (2022-08-08T03:13:24Z)
• RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging [36.027765880474526]
  Pruning Deep Neural Networks (DNNs) is a prominent field of study in the goal of inference runtime acceleration. We introduce a novel data-free pruning protocol RED++. We study the theoretical and empirical guarantees on the preservation of the accuracy from the hashing.
  arXiv  Detail & Related papers  (2021-09-30T09:31:11Z)
• GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization [84.57695474130273]
  Gate-based or importance-based pruning methods aim to remove channels whose importance is smallest. GDP can be plugged before convolutional layers without bells and whistles, to control the on-and-off of each channel. Experiments conducted over CIFAR-10 and ImageNet datasets show that the proposed GDP achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-09-06T03:17:10Z)
• Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming [97.40955121478716]
  We propose a first-order dual SDP algorithm that requires memory only linear in the total number of network activations. We significantly improve L-inf verified robust accuracy from 1% to 88% and 6% to 40% respectively. We also demonstrate tight verification of a quadratic stability specification for the decoder of a variational autoencoder.
  arXiv  Detail & Related papers  (2020-10-22T12:32:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.