RLAA is a localized adversarial anonymization framework that adds an arbitrator to filter ghost leaks and enforce rational early stopping, yielding superior privacy-utility trade-offs on benchmarks compared to greedy baselines.
InFindings of the Association for Computa- tional Linguistics: NAACL 2024, pages 2433–2462
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Look Twice before You Leap: A Rational Framework for Localized Adversarial Anonymization
RLAA is a localized adversarial anonymization framework that adds an arbitrator to filter ghost leaks and enforce rational early stopping, yielding superior privacy-utility trade-offs on benchmarks compared to greedy baselines.