Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
An Efficient and Accurate Gated RNN for Execution under TFHE
RISE Research Institutes of Sweden, Digital Systems, Data Science.ORCID iD: 0000-0003-4293-6408
Zama, Machine Learning Group, Paris, France.
2024 (English)Conference paper, Published paper (Other academic)
Abstract [en]

We implement and test the recently proposed Inhibitor gate for Recurrent Neural Networks (RNNs) that is both efficient and accurate under Homomorphic Encryption. Gated RNNs such as LSTM and GRU have applications in numerous real-world use cases for sequential data, such as time-series analysis and natural language processing, due to their ability to capture long-term dependencies. Conventionally, the update based on current inputs and the previous state history is each multiplied with the dynamic gate values and combined to compute the next state. However, as it is a multiplication between two variables that depend on the input, it can be com-putationally expensive, especially under homomorphic en-cryption, where it involves a multiplication between two cipher text variables. Therefore, the novel gating mechanism replaces the multiplication and sigmoid function of the conventional RNN with addition and ReLU activation. Numerical experiments on three synthetic benchmark tests demonstrate that our algorithm outperforms a conventional gated RNN showing at least an order of magnitude faster execution already at 4-bit quantization. At a fixed computational budget , we get 7-bit precision with the novel gate that executes faster than the 4-bit conventional gate. The gating mechanism employed in this paper may enable privacy-preserving AI applications based on gated RNNs operating under homomorphic encryption by avoiding the multiplication of encrypted variables.

Place, publisher, year, edition, pages
2024.
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:ri:diva-79018OAI: oai:DiVA.org:ri-79018DiVA, id: diva2:1999682
Conference
PPAI-24: The 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence
Available from: 2025-09-22 Created: 2025-09-22 Last updated: 2025-09-23Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Research Gate

Authority records

Brännvall, Rickard

Search in DiVA

By author/editor
Brännvall, Rickard
By organisation
Data Science
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 84 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf