Pith. sign in

REVIEW

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2202.06924 v3 pith:UWWHDGCP submitted 2022-02-14 cs.LG cs.CRcs.CVcs.DC

classification cs.LGcs.CRcs.CVcs.DC
keywords dataleakagetrainingattacksfederatedinversionlearningmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern. However, recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training data. In this work, we show that these attacks presented in the literature are impractical in FL use-cases where the clients' training involves updating the Batch Normalization (BN) statistics and provide a new baseline attack that works for such scenarios. Furthermore, we present new ways to measure and visualize potential data leakage in FL. Our work is a step towards establishing reproducible methods of measuring data leakage in FL and could help determine the optimal tradeoffs between privacy-preserving techniques, such as differential privacy, and model accuracy based on quantifiable metrics. Code is available at https://nvidia.github.io/NVFlare/research/quantifying-data-leakage.

Discussion (0). Continue with ORCID to comment.

Pith tools