THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption
read the original abstract
As more and more pre-trained language models adopt on-cloud deployment, the privacy issues grow quickly, mainly for the exposure of plain-text user data (e.g., search history, medical record, bank account). Privacy-preserving inference of transformer models is on the demand of cloud service users. To protect privacy, it is an attractive choice to compute only with ciphertext in homomorphic encryption (HE). However, enabling pre-trained models inference on ciphertext data is difficult due to the complex computations in transformer blocks, which are not supported by current HE tools yet. In this work, we introduce $\textit{THE-X}$, an approximation approach for transformers, which enables privacy-preserving inference of pre-trained models developed by popular frameworks. $\textit{THE-X}$ proposes a workflow to deal with complex computation in transformer networks, including all the non-polynomial functions like GELU, softmax, and LayerNorm. Experiments reveal our proposed $\textit{THE-X}$ can enable transformer inference on encrypted data for different downstream tasks, all with negligible performance drop but enjoying the theory-guaranteed privacy-preserving advantage.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
Power-Softmax: Towards Secure LLM Inference over Encrypted Data
Power-Softmax is a new HE-compatible attention variant that permits training and inference of billion-parameter polynomial LLMs with performance matching standard transformers.
-
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
-
Beyond Latency: A System-Level Characterization of MPC and FHE for PPML
System-level evaluation reveals that network constraints and hardware costs, rather than raw latency, often dictate the optimal choice between MPC and FHE for privacy-preserving ML.
-
ConfusionPrompt: Practical Private Inference for Online Large Language Models
ConfusionPrompt enables private black-box LLM inference via prompt decomposition and pseudo-prompt mixing, claiming better privacy-utility trade-off than perturbation methods and lower memory use than open-source loca...
-
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
SharedRequest is a model-agnostic batch-level framework that mixes prompts with noise and groups equivalent instructions to achieve higher utility and lower query cost than individual differential privacy methods for ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.