SPIA benchmark reveals that subject-level inference protection falls to as low as 33% even after masking over 90% of PII spans, with non-target subjects remaining highly exposed under target-focused anonymization.
InProceedings of the IEEE International Conference on Big Data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Subject-level Inference for Realistic Text Anonymization Evaluation
SPIA benchmark reveals that subject-level inference protection falls to as low as 33% even after masking over 90% of PII spans, with non-target subjects remaining highly exposed under target-focused anonymization.