A GAN-inspired pipeline that uses a grammar fuzzer instead of a learned generator can produce tabular data with competitive utility, but the claimed privacy protection is not established.
Title resolution pending
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SecretFan: Synthesizing Realistic Data without Breaking Privacy
A GAN-inspired pipeline that uses a grammar fuzzer instead of a learned generator can produce tabular data with competitive utility, but the claimed privacy protection is not established.