Metraipolis › archive › dc_1dbb23b4e2b8
PPQformer: Privacy-Preserving Quantized Transformer for Efficient and Secure Inference. (2025) · OpenAlex W4411016730
- Source
- OpenAlex
- Original
- https://doi.org/10.1145/3728725.3728743
- License (as archived)
- CC-BY-4.0
- Archived
- 2026-10-08T03:11:32.647Z
- SHA-256 of the archived text
3fdcec1b87f315370c7e752a1ca3087aed3eab4935f65723c10f0e9ced2e816b- Stable URL of this page
https://metraipolis.com/documento/dc_1dbb23b4e2b8
How to cite
PPQformer: Privacy-Preserving Quantized Transformer for Efficient and Secure Inference. (2025) · OpenAlex W4411016730 — OpenAlex, https://doi.org/10.1145/3728725.3728743 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_1dbb23b4e2b8 (Metraipolis archive dc_1dbb23b4e2b8, sha256 3fdcec1b87f315370c7e752a1ca3087aed3eab4935f65723c10f0e9ced2e816b)
BibTeX
@misc{dc1dbb23b4e2b8,
title = {PPQformer: Privacy-Preserving Quantized Transformer for Efficient and Secure Inference. (2025) · OpenAlex W4411016730},
howpublished = {OpenAlex},
url = {https://doi.org/10.1145/3728725.3728743},
note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_1dbb23b4e2b8; sha256 3fdcec1b87f315370c7e752a1ca3087aed3eab4935f65723c10f0e9ced2e816b},
year = {2026}
}Archived text
Reproduced under CC-BY-4.0. Attribution: OpenAlex, https://doi.org/10.1145/3728725.3728743. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Opera scientifica in accesso aperto: scheda dai metadati OpenAlex (conference-paper). Titolo: PPQformer: Privacy-Preserving Quantized Transformer for Efficient and Secure Inference. Autori: Benchang Dong, Zhili Chen Anno: 2025 · Sede: International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · Lingua: en DOI: https://doi.org/10.1145/3728725.3728743 Accesso aperto: hybrid · testo: https://doi.org/10.1145/3728725.3728743 · licenza del testo: cc-by Citazioni ricevute (OpenAlex): 1 Temi (OpenAlex): Cryptography and Data Security; Privacy-Preserving Technologies in Data; Cloud Data Security Solutions Abstract (testo degli autori, licenza cc-by): In the context of the popularity of Transformer model services, the issue of privacy protection has gradually gained attention. However, the primary issues with existing private inference solutions lie in memory constraints and suboptimal computational performance. In this work, we introduce PPQformer, a framework that leverages Replicated Secret Sharing (RSS) and quantization techniques to enable efficient and secure inference of Transformer models in a Multi-Party Computation (MPC) setting. By integrating quantization into the MPC protocols, PPQformer significantly reduces memory footprint and enhances computational performance while preserving data and model privacy. Experimental results demonstrate the effectiveness of our approach, achieving competitive accuracies with reduced communication cost and inference time compared to existing methods. Fonte: https://openalex.org/W4411016730 — metadati OpenAlex (CC0 1.0), consultati il 2026-10-07 via api.openalex.org. Interrogazione: «efficient inference quantization».