All You Need Is Hashing: Defending Against Data Reconstruction Attack in Vertical Federated Learning

by   Pengyu Qiu, et al.

Vertical federated learning is a trending solution for multi-party collaboration in training machine learning models. Industrial frameworks adopt secure multi-party computation methods such as homomorphic encryption to guarantee data security and privacy. However, a line of work has revealed that there are still leakage risks in VFL. The leakage is caused by the correlation between the intermediate representations and the raw data. Due to the powerful approximation ability of deep neural networks, an adversary can capture the correlation precisely and reconstruct the data. To deal with the threat of the data reconstruction attack, we propose a hashing-based VFL framework, called HashVFL, to cut off the reversibility directly. The one-way nature of hashing allows our framework to block all attempts to recover data from hash codes. However, integrating hashing also brings some challenges, e.g., the loss of information. This paper proposes and addresses three challenges to integrating hashing: learnability, bit balance, and consistency. Experimental results demonstrate HashVFL's efficiency in keeping the main task's performance and defending against data reconstruction attacks. Furthermore, we also analyze its potential value in detecting abnormal inputs. In addition, we conduct extensive experiments to prove HashVFL's generalization in various settings. In summary, HashVFL provides a new perspective on protecting multi-party's data security and privacy in VFL. We hope our study can attract more researchers to expand the application domains of HashVFL.


page 1

page 7

page 16


Defending against Reconstruction Attack in Vertical Federated Learning

Recently researchers have studied input leakage problems in Federated Le...

Quadratic Functional Encryption for Secure Training in Vertical Federated Learning

Vertical federated learning (VFL) enables the collaborative training of ...

Practical and General Backdoor Attacks against Vertical Federated Learning

Federated learning (FL), which aims to facilitate data collaboration acr...

Privacy Leakage of Real-World Vertical Federated Learning

Federated learning enables mutually distrusting participants to collabor...

Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm

Vertical federated learning (VFL) attracts increasing attention due to t...

Label Inference Attack against Split Learning under Regression Setting

As a crucial building block in vertical Federated Learning (vFL), Split ...

Knowledge Federation: Hierarchy and Unification

With the strengthening of data privacy and security, traditional data ce...

Please sign up or login with your details

Forgot password? Click here to reset