Input Reconstruction Attack against Vertical Federated Large Language Models
Recently, large language models (LLMs) have drawn extensive attention from academia and the public, due to the advent of the ChatGPT. While LLMs show their astonishing ability in text generation for various tasks, privacy concerns limit their usage in real-life businesses. More specifically, either the user's inputs (the user sends the query to the model-hosting server) or the model (the user downloads the complete model) itself will be revealed during the usage. Vertical federated learning (VFL) is a promising solution to this kind of problem. It protects both the user's input and the knowledge of the model by splitting the model into a bottom part and a top part, which is maintained by the user and the model provider, respectively. However, in this paper, we demonstrate that in LLMs, VFL fails to protect the user input since it is simple and cheap to reconstruct the input from the intermediate embeddings. Experiments show that even with a commercial GPU, the input sentence can be reconstructed in only one second. We also discuss several possible solutions to enhance the privacy of vertical federated LLMs.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningGPUReconstruction AttackSentenceText GenerationVertical Federated LearningSimilar Papers 제목 키워드 기반
Defending against Reconstruction Attack in Vertical Federated Learning
Recently researchers have studied input leakage problems in Federated Learning (FL) where a malicious party can reconstruct sensitive training inputs provided by users from shared gradient. It raises concerns about FL si…
Federated LearningPrivacy PreservingReconstruction AttackVertical Federated LearningPRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks
Vertical Federated Learning (VFL) enables collaborative model training across organizations that share common user samples but hold disjoint feature spaces. Despite its potential, VFL is susceptible to feature inference …
Federated LearningJust a Simple Transformation is Enough for Data Protection in Vertical Federated Learning
Vertical Federated Learning (VFL) aims to enable collaborative training of deep learning models while maintaining privacy protection. However, the VFL procedure still has components that are vulnerable to attacks by mali…
Federated LearningPrivacy Preserving Deep LearningVertical Federated LearningHashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial frameworks employ secure multi-party computation techniques such as homomorphic encryption to en…
Federated LearningReconstruction AttackVertical Federated LearningFeature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning
Federated learning (FL) has increasingly been deployed, in its vertical form, among organizations to facilitate secure collaborative training over siloed data. In vertical FL (VFL), participants hold disjoint features of…
Federated LearningReconstruction AttackVertical Federated Learning