On protecting the data privacy of large language models (llms): A survey
Large language models (LLMs) are complex artificial intelligence systems capable of
understanding, generating and translating human language. They learn language patterns …
understanding, generating and translating human language. They learn language patterns …
Towards practical secure neural network inference: the journey so far and the road ahead
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 …
intelligence. Well-designed and trained NNs can perform inference (eg, make decisions or …
Bolt: Privacy-preserving, accurate and efficient inference for transformers
The advent of transformers has brought about significant advancements in traditional
machine learning tasks. However, their pervasive deployment has raised concerns about …
machine learning tasks. However, their pervasive deployment has raised concerns about …
Privacy in large language models: Attacks, defenses and future directions
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 …
effectively tackle various downstream NLP tasks and unify these tasks into generative …
Bumblebee: Secure two-party inference framework for large transformers
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 …
world tasks such as natural language processing and computer vision. However, with the …
Complex QA and language models hybrid architectures, Survey
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 …
complex" question-answering (QA, CQA, CPS) with a focus on hybridization. Large …
Ciphergpt: Secure two-party gpt inference
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 …
raises serious concerns regarding user privacy, as the data submitted by users may contain …
Secure transformer inference made non-interactive
Secure transformer inference has emerged as a prominent research topic following the
proliferation of ChatGPT. Existing solutions are typically interactive, involving substantial …
proliferation of ChatGPT. Existing solutions are typically interactive, involving substantial …
Mpcvit: Searching for accurate and efficient mpc-friendly vision transformer with heterogeneous attention
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 …
protects both data and model privacy in deep learning inference. However, existing neural …
Grounding foundation models through federated transfer learning: A general framework
Foundation Models (FMs) such as GPT-4 encoded with vast knowledge and powerful
emergent abilities have achieved remarkable success in various natural language …
emergent abilities have achieved remarkable success in various natural language …