Encrypted Large Model Inference: The Equivariant Encryption Paradigm

• URL: http://arxiv.org/abs/2502.01013v1
• Date: Mon, 03 Feb 2025 03:05:20 GMT
• Title: Encrypted Large Model Inference: The Equivariant Encryption Paradigm
• Authors: James Buban, Hongyang Zhang, Claudio Angione, Harry Yang, Ahmad Farhan, Seyfal Sultanov, Michael Du, Xuran Ma, Zihao Wang, Yue Zhao, Arria Owlia, Fielding Johnston, Patrick Colangelo,
• Abstract summary: We introduce Equivariant Encryption (EE), a novel paradigm designed to enable secure, "blind" inference on encrypted data with near zero performance overhead. Unlike fully homomorphic approaches that encrypt the entire computational graph, EE selectively obfuscates critical internal representations within neural network layers. EE maintains high fidelity and throughput, effectively bridging the gap between robust data confidentiality and the stringent efficiency requirements of modern, large scale model inference.
• Score: 18.547945807599543
• License:
• Abstract: Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer vision. However, their deployment in distributed or decentralized environments raises significant privacy concerns, as sensitive data may be exposed during inference. Traditional techniques like secure multi-party computation, homomorphic encryption, and differential privacy offer partial remedies but often incur substantial computational overhead, latency penalties, or limited compatibility with non-linear network operations. In this work, we introduce Equivariant Encryption (EE), a novel paradigm designed to enable secure, "blind" inference on encrypted data with near zero performance overhead. Unlike fully homomorphic approaches that encrypt the entire computational graph, EE selectively obfuscates critical internal representations within neural network layers while preserving the exact functionality of both linear and a prescribed set of non-linear operations. This targeted encryption ensures that raw inputs, intermediate activations, and outputs remain confidential, even when processed on untrusted infrastructure. We detail the theoretical foundations of EE, compare its performance and integration complexity against conventional privacy preserving techniques, and demonstrate its applicability across a range of architectures, from convolutional networks to large language models. Furthermore, our work provides a comprehensive threat analysis, outlining potential attack vectors and baseline strategies, and benchmarks EE against standard inference pipelines in decentralized settings. The results confirm that EE maintains high fidelity and throughput, effectively bridging the gap between robust data confidentiality and the stringent efficiency requirements of modern, large scale model inference.

Related papers

• Encryption-Friendly LLM Architecture [11.386436468650016]
  Homomorphic encryption (HE) is a cryptographic protocol supporting arithmetic computations in encrypted states. We propose a modified HE-friendly transformer architecture with an emphasis on inference following personalized (private) fine-tuning.
  arXiv  Detail & Related papers  (2024-10-03T13:48:35Z)
• Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inference [11.39873199479642]
  Nesa introduces a model-agnostic sharding framework designed for decentralized AI inference. Our framework uses blockchain-based deep neural network sharding to distribute computational tasks across a diverse network of nodes. Our results highlight the potential to democratize access to cutting-edge AI technologies.
  arXiv  Detail & Related papers  (2024-07-29T08:18:48Z)
• EncCluster: Scalable Functional Encryption in Federated Learning through Weight Clustering and Probabilistic Filters [3.9660142560142067]
  Federated Learning (FL) enables model training across decentralized devices by communicating solely local model updates to an aggregation server. FL remains vulnerable to inference attacks during model update transmissions. We present EncCluster, a novel method that integrates model compression through weight clustering with recent decentralized FE and privacy-enhancing data encoding.
  arXiv  Detail & Related papers  (2024-06-13T14:16:50Z)
• When approximate design for fast homomorphic computation provides differential privacy guarantees [0.08399688944263842]
  Differential privacy (DP) and cryptographic primitives are popular countermeasures against privacy attacks. In this paper, we design SHIELD, a probabilistic approximation algorithm for the argmax operator. Even if SHIELD could have other applications, we here focus on one setting and seamlessly integrate it in the SPEED collaborative training framework.
  arXiv  Detail & Related papers  (2023-04-06T09:38:01Z)
• Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond [57.10914865054868]
  We consider vertical logistic regression (VLR) trained with mini-batch descent gradient. We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks.
  arXiv  Detail & Related papers  (2022-07-19T05:47:30Z)
• THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption [112.02441503951297]
  Privacy-preserving inference of transformer models is on the demand of cloud service users. We introduce $textitTHE-X$, an approximation approach for transformers, which enables privacy-preserving inference of pre-trained models.
  arXiv  Detail & Related papers  (2022-06-01T03:49:18Z)
• Deep Equilibrium Assisted Block Sparse Coding of Inter-dependent Signals: Application to Hyperspectral Imaging [71.57324258813675]
  A dataset of inter-dependent signals is defined as a matrix whose columns demonstrate strong dependencies. A neural network is employed to act as structure prior and reveal the underlying signal interdependencies. Deep unrolling and Deep equilibrium based algorithms are developed, forming highly interpretable and concise deep-learning-based architectures.
  arXiv  Detail & Related papers  (2022-03-29T21:00:39Z)
• Reinforcement Learning on Encrypted Data [58.39270571778521]
  We present a preliminary, experimental study of how a DQN agent trained on encrypted states performs in environments with discrete and continuous state spaces. Our results highlight that the agent is still capable of learning in small state spaces even in presence of non-deterministic encryption, but performance collapses in more complex environments.
  arXiv  Detail & Related papers  (2021-09-16T21:59:37Z)
• Efficient CNN Building Blocks for Encrypted Data [6.955451042536852]
  Homomorphic Encryption (FHE) is a promising technique to enable machine learning and inferencing. We show that operational parameters of the chosen FHE scheme have a major impact on the design of the machine learning model. Our empirical study shows that choice of aforementioned design parameters result in significant trade-offs between accuracy, security level, and computational time.
  arXiv  Detail & Related papers  (2021-01-30T21:47:23Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)
• CryptoSPN: Privacy-preserving Sum-Product Network Inference [84.88362774693914]
  We present a framework for privacy-preserving inference of sum-product networks (SPNs) CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.
  arXiv  Detail & Related papers  (2020-02-03T14:49:18Z)

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.