Subject-level Inference for Realistic Text Anonymization Evaluation
Current text anonymization evaluation relies on span-based metrics that fail to capture what an adversary could actually infer, and assumes a single data subject, ignoring multi-subject scenarios. To address these limitations, we present SPIA (Subject-level PII Inference Assessment), the first benchmark that shifts the unit of evaluation from text spans to individuals, comprising 675 documents across legal and online domains with novel subject-level protection metrics. Extensive experiments show that even when over 90% of PII spans are masked, subject-level inference protection drops as low as 33%, leaving the majority of personal information recoverable through contextual inference. Furthermore, target-subject-focused anonymization leaves non-target subjects substantially more exposed than the target subject. We show that subject-level inference-based evaluation is essential for ensuring safe text anonymization in real-world settings.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Reverse Personalization
Recent text-to-image diffusion models have demonstrated remarkable generation of realistic facial images conditioned on textual prompts and human identities, enabling creating personalized facial imagery. However, existi…
Face AnonymizationLarge Language Models are Advanced Anonymizers
Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonym…
Text AnonymizationDeepPrivacy2: Towards Realistic Full-Body Anonymization
Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures. However, current state-of-the-art limit anonymization to the task of face anonymization. In this paper, we propose a novel ano…
DiversityFace AnonymizationFull-body anonymizationDoes Image Anonymization Impact Computer Vision Training?
Image anonymization is widely adapted in practice to comply with privacy regulations in many regions. However, anonymization often degrades the quality of the data, reducing its utility for computer vision development. I…
Face AnonymizationInstance SegmentationPose EstimationPrivacy Preserving+1Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
Cameras are prevalent in our daily lives, and enable many useful systems built upon computer vision technologies such as smart cameras and home robots for service applications. However, there is also an increasing societ…
Multi-Task Learning