Gradient Obfuscation Gives a False Sense of Security in Federated Learning Article Swipe

MAKE IMPACT

Kai Yue , Richeng Jin , Chau-Wai Wong , Dror Baron , Huaiyu Dai · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2206.04055

Federated learning has been proposed as a privacy-preserving machine learning framework that enables multiple clients to collaborate without sharing raw data. However, client privacy protection is not guaranteed by design in this framework. Prior work has shown that the gradient sharing strategies in federated learning can be vulnerable to data reconstruction attacks. In practice, though, clients may not transmit raw gradients considering the high communication cost or due to privacy enhancement requirements. Empirical studies have demonstrated that gradient obfuscation, including intentional obfuscation via gradient noise injection and unintentional obfuscation via gradient compression, can provide more privacy protection against reconstruction attacks. In this work, we present a new data reconstruction attack framework targeting the image classification task in federated learning. We show that commonly adopted gradient postprocessing procedures, such as gradient quantization, gradient sparsification, and gradient perturbation, may give a false sense of security in federated learning. Contrary to prior studies, we argue that privacy enhancement should not be treated as a byproduct of gradient compression. Additionally, we design a new method under the proposed framework to reconstruct the image at the semantic level. We quantify the semantic privacy leakage and compare with conventional based on image similarity scores. Our comparisons challenge the image data leakage evaluation schemes in the literature. The results emphasize the importance of revisiting and redesigning the privacy protection mechanisms for client data in existing federated learning algorithms.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2206.04055

PDF

https://arxiv.org/pdf/2206.04055

OA Status

green

Cited By

13

Related Works

10

OpenAlex ID

https://openalex.org/W4281609047

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4281609047

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2206.04055

Digital Object Identifier

Title

Gradient Obfuscation Gives a False Sense of Security in Federated Learning

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-06-08

Full publication date if available

Authors

Kai Yue, Richeng Jin, Chau-Wai Wong, Dror Baron, Huaiyu Dai

List of authors in order

Landing page

https://arxiv.org/abs/2206.04055

Publisher landing page

PDF URL

https://arxiv.org/pdf/2206.04055

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2206.04055

Direct OA link when available

Concepts

Computer science, Obfuscation, Quantization (signal processing), Data sharing, Machine learning, Artificial intelligence, Differential privacy, Information privacy, Raw data, Computer security, Data mining, Algorithm, Alternative medicine, Pathology, Medicine, Programming language

Top concepts (fields/topics) attached by OpenAlex

Cited by

13

Total citation count in OpenAlex

Citations by year (recent)

2025: 5, 2024: 5, 2023: 3

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload