Privacy-Preserving Language Model Inference with Instance Obfuscation
Language Models as a Service (LMaaS) offers convenient access for developers and researchers to perform inference using pre-trained language models. Nonetheless, the input data and the inference results containing private information are exposed as plaintext during the service call, leading to privacy issues. Recent studies have started tackling the privacy issue by transforming input data into privacy-preserving representation from the user-end with the techniques such as noise addition and content perturbation, while the exploration of inference result protection, namely decision privacy, is still a blank page. In order to maintain the black-box manner of LMaaS, conducting data privacy protection, especially for the decision, is a challenging task because the process has to be seamless to the models and accompanied by limited communication and computation overhead. We thus propose Instance-Obfuscated Inference (IOI) method, which focuses on addressing the decision privacy issue of natural language understanding tasks in their complete life-cycle. Besides, we conduct comprehensive experiments to evaluate the performance as well as the privacy-protection strength of the proposed method on various benchmarking tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingLanguage ModelingLanguage ModellingmodelNatural Language UnderstandingPrivacy PreservingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
HyObscure: Hybrid Obscuring for Privacy-Preserving Data Publishing
Minimizing privacy leakage while ensuring data utility is a critical problem to data holders in a privacy-preserving data publishing task. Most prior research concerns only with one type of data and resorts to a single o…
Privacy PreservingTowards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)
The rapid development of large language models (LLMs) has driven the widespread adoption of cloud-based LLM inference services, while also bringing prominent privacy risks associated with the transmission and processing …
FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation
Vertical federated learning (VFL) allows an active party with labeled feature to leverage auxiliary features from the passive parties to improve model performance. Concerns about the private feature and label leakage in …
Deep LearningFederated LearningPrivacy PreservingVertical Federated LearningPrivacy-Preserving Obfuscation of Critical Infrastructure Networks
The paper studies how to release data about a critical infrastructure network (e.g., the power network or a transportation network) without disclosing sensitive information that can be exploited by malevolent agents, whi…
Privacy PreservingTechnical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine Learning
The right to privacy, enshrined in various human rights declarations, faces new challenges in the age of artificial intelligence (AI). This paper explores the concept of the Right to be Forgotten (RTBF) within AI systems…
Inference AttackMachine UnlearningMembership Inference AttackPrivacy Preserving