Confidential Prompting: Protecting User Prompts from Cloud LLM Providers
Our work tackles the challenge of securing user inputs in cloud-hosted large language model (LLM) serving while ensuring model confidentiality, output invariance, and compute efficiency. We introduce Secure Partitioned Decoding (SPD), which uses confidential computing to confine user prompts to a trusted execution environment (TEE), namely a confidential virtual machine (CVM), while allowing service providers to generate tokens efficiently. We also introduce a novel cryptographic method, Prompt Obfuscation (PO), to ensure robustness against reconstruction attacks on SPD. We demonstrate our approach preserves both prompt confidentiality and LLM serving efficiency. Our solution enables privacy-preserving cloud LLM serving that handles sensitive prompts, such as clinical records, financial data, and personal information.
Code (1)
Tasks
Language ModelingLanguage ModellingLarge Language ModelPrivacy PreservingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Confidential Boosting with Random Linear Classifiers for Outsourced User-generated Data
User-generated data is crucial to predictive modeling in many applications. With a web/mobile/wearable interface, a data owner can continuously record data generated by distributed users and build various predictive mode…
QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety
The recent advancements in Large Language Models(LLMs) have had a significant impact on a wide range of fields, from general domains to specialized areas. However, these advancements have also significantly increased the…
Privacy-Enhancing Fall Detection from Remote Sensor Data Using Multi-Party Computation
Motion-based fall detection systems are concerned with detecting falls from vulnerable users, which is typically performed by classifying measurements from a body-worn inertial measurement unit (IMU) using machine learni…
Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models
The increasing reliance on cloud-hosted Large Language Models (LLMs) exposes sensitive client data, such as prompts and responses, to potential privacy breaches by service providers. Existing approaches fail to ensure pr…
Computational EfficiencyPractical and Private Hybrid ML Inference with Fully Homomorphic Encryption
In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. Fully homomorphic encryption (FHE) enables inference directly on encrypted input…