On protecting the data privacy of large language models (llms): A survey

B Yan, K Li, M Xu, Y Dong, Y Zhang, Z Ren… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) are complex artificial intelligence systems capable of
understanding, generating and translating human language. They learn language patterns …

Towards practical secure neural network inference: the journey so far and the road ahead

ZÁ Mann, C Weinert, D Chabal, JW Bos - ACM Computing Surveys, 2023 - dl.acm.org
Neural networks (NNs) have become one of the most important tools for artificial
intelligence. Well-designed and trained NNs can perform inference (eg, make decisions or …

Bolt: Privacy-preserving, accurate and efficient inference for transformers

Q Pang, J Zhu, H Möllering, W Zheng… - … IEEE Symposium on …, 2024 - ieeexplore.ieee.org
The advent of transformers has brought about significant advancements in traditional
machine learning tasks. However, their pervasive deployment has raised concerns about …

Privacy in large language models: Attacks, defenses and future directions

H Li, Y Chen, J Luo, J Wang, H Peng, Y Kang… - arxiv preprint arxiv …, 2023 - arxiv.org
The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …

Bumblebee: Secure two-party inference framework for large transformers

W Lu, Z Huang, Z Gu, J Li, J Liu, C Hong… - Cryptology ePrint …, 2023 - eprint.iacr.org
Large transformer-based models have realized state-of-the-art performance on lots of real-
world tasks such as natural language processing and computer vision. However, with the …

Complex QA and language models hybrid architectures, Survey

X Daull, P Bellot, E Bruno, V Martin… - arxiv preprint arxiv …, 2023 - arxiv.org
This paper reviews the state-of-the-art of language models architectures and strategies for"
complex" question-answering (QA, CQA, CPS) with a focus on hybridization. Large …

Ciphergpt: Secure two-party gpt inference

X Hou, J Liu, J Li, Y Li, W Lu, C Hong… - Cryptology ePrint …, 2023 - eprint.iacr.org
ChatGPT is recognized as a significant revolution in the field of artificial intelligence, but it
raises serious concerns regarding user privacy, as the data submitted by users may contain …

Secure transformer inference made non-interactive

J Zhang, X Yang, L He, K Chen, W Lu… - Cryptology ePrint …, 2024 - eprint.iacr.org
Secure transformer inference has emerged as a prominent research topic following the
proliferation of ChatGPT. Existing solutions are typically interactive, involving substantial …

Mpcvit: Searching for accurate and efficient mpc-friendly vision transformer with heterogeneous attention

W Zeng, M Li, W **ong, T Tong, W Lu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Secure multi-party computation (MPC) enables computation directly on encrypted data and
protects both data and model privacy in deep learning inference. However, existing neural …

Grounding foundation models through federated transfer learning: A general framework

Y Kang, T Fan, H Gu, X Zhang, L Fan… - arxiv preprint arxiv …, 2023 - arxiv.org
Foundation Models (FMs) such as GPT-4 encoded with vast knowledge and powerful
emergent abilities have achieved remarkable success in various natural language …