mlsanityData to 7 Oct 2026

Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations

arXiv 2206.05893 ↗First posted 13 Jun 2022cs.LG cs.CR cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Due to the computational cost of running inference for a neural network, the need to deploy the inferential steps on a third party's compute environment or hardware is common. If the third party is not fully trusted, it is desirable to obfuscate the nature of the inputs and outputs, so that the third party can not easily determine what specific task is being performed. Provably secure protocols for leveraging an untrusted party exist but are too computational demanding to run in practice. We instead explore a different strategy of fast, heuristic security that we call Connectionist Symbolic Pseudo Secrets. By leveraging Holographic Reduced Representations (HRR), we create a neural network with a pseudo-encryption style defense that empirically shows robustness to attack, even under threat models that unrealistically favor the adversary.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

19 of 39 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  5. 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 260
  6. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  7. 2020InstaHide: Instance-hiding Schemes for Private Distributed Learningcited by 90
  8. 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
  9. 2018Low Latency Privacy Preserving Inferencecited by 57
  10. 2019XONN: XNOR-based Oblivious Deep Neural Network Inferencecited by 51
  11. 2021TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryptioncited by 51
  12. 2017DeepSecure: Scalable Provably-Secure Deep Learningcited by 48
7 more
  1. 2018Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inferencecited by 45
  2. 2017Security Evaluation of Pattern Classifiers under Attackcited by 39
  3. 2021Learning with Holographic Reduced Representationscited by 25
  4. 2018Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUscited by 11
  5. 2019SEALion: a Framework for Neural Network Inference on Encrypted Datacited by 9
  6. 2017Encrypted accelerated least squares regressioncited by 2
  7. 2021Exact Acceleration of K-Means++ and K-Means|cited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 2; 2025: 1.

7 papers.

  1. 2023MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superpositioncited by 14
  2. 2024Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detectioncited by 6
  3. 2023Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representationscited by 4
  4. 2024A Walsh Hadamard Derived Linear Vector Symbolic Architecturecited by 4
  5. 2022Lempel-Ziv Networkscited by 3
  6. 2023Finding Meaningful Distributions of ML Black-boxes under Forensic Investigationcited by 1
  7. 2025A Vector Symbolic Approach to Multiple Instance Learningcited by 0