Pith. sign in

REVIEW

Extracted BERT Model Leaks More Information than You Think!

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 2210.11735 v2 pith:QNWHE4UY submitted 2022-10-21 cs.CR

classification cs.CR
keywords modelbertextractionmodelsbeenextractedleakageperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning as a service (MLaaS) by encapsulating fine-tuned BERT-based models as APIs. Due to significant commercial interest, there has been a surge of attempts to steal re mote services via model extraction. Although previous works have made progress in defending against model extraction attacks, there has been little discussion on their performance in preventing privacy leakage. This work bridges this gap by launching an attribute inference attack against the extracted BERT model. Our extensive experiments reveal that model extraction can cause severe privacy leakage even when victim models are facilitated with advanced defensive strategies.

Discussion (0). Continue with ORCID to comment.

Pith tools