Unmasking the Reality of PII Masking Models: Performance Gaps and the Call for Accountability

• URL: http://arxiv.org/abs/2504.12308v1
• Date: Sat, 05 Apr 2025 04:34:05 GMT
• Title: Unmasking the Reality of PII Masking Models: Performance Gaps and the Call for Accountability
• Authors: Devansh Singh, Sundaraparipurnan Narayanan,
• Abstract summary: We present a dataset of 17K unique, semi-synthetic sentences containing 16 types of PII.<n>We generate sentences containing these PII at five different NER detection feature dimensions.<n>We show the results and exhibit the privacy exposure caused by such model use.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Privacy Masking is a critical concept under data privacy involving anonymization and de-anonymization of personally identifiable information (PII). Privacy masking techniques rely on Named Entity Recognition (NER) approaches under NLP support in identifying and classifying named entities in each text. NER approaches, however, have several limitations including (a) content sensitivity including ambiguous, polysemic, context dependent or domain specific content, (b) phrasing variabilities including nicknames and alias, informal expressions, alternative representations, emerging expressions, evolving naming conventions and (c) formats or syntax variations, typos, misspellings. However, there are a couple of PII datasets that have been widely used by researchers and the open-source community to train models on PII detection or masking. These datasets have been used to train models including Piiranha and Starpii, which have been downloaded over 300k and 580k times on HuggingFace. We examine the quality of the PII masking by these models given the limitations of the datasets and of the NER approaches. We curate a dataset of 17K unique, semi-synthetic sentences containing 16 types of PII by compiling information from across multiple jurisdictions including India, U.K and U.S. We generate sentences (using language models) containing these PII at five different NER detection feature dimensions - (1) Basic Entity Recognition, (2) Contextual Entity Disambiguation, (3) NER in Noisy & Real-World Data, (4) Evolving & Novel Entities Detection and (5) Cross-Lingual or multi-lingual NER) and 1 in adversarial context. We present the results and exhibit the privacy exposure caused by such model use (considering the extent of lifetime downloads of these models). We conclude by highlighting the gaps in measuring performance of the models and the need for contextual disclosure in model cards for such models.

Related papers

• Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings [0.0]
  This paper proposes a framework for uncovering the specific dimensions of vector embeddings that encode distinct linguistic properties (LPs) We introduce the Linguistically Distinct Sentence Pairs dataset, which isolates ten key linguistic features such as synonymy, negation, tense, and quantity. Using this dataset, we analyze BERT embeddings with various methods to identify the most influential dimensions for each LP. Our findings show that certain properties, such as negation and polarity, are robustly encoded in specific dimensions, while others, like synonymy, exhibit more complex patterns.
  arXiv  Detail & Related papers  (2025-04-20T23:38:16Z)
• Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation [66.66243874361103]
  dataset generation faces two key challenges: 1) aligning generated samples with the target domain and 2) producing informative samples beyond the training data. We propose Concept-Aware LoRA, a novel fine-tuning approach that selectively identifies and updates only the weights associated with necessary concepts for domain alignment. We demonstrate its effectiveness in generating datasets for urban-scene segmentation, outperforming baseline and state-of-the-art methods in in-domain settings.
  arXiv  Detail & Related papers  (2025-03-28T06:23:29Z)
• TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models [12.497110441765274]
  Existing methods for identity inference in CLIP models require querying the model with full PII.<n>Applying images may risk exposing personal information to target models, as the image might not have been previously encountered by the target model.<n>We propose a textual unimodal detector (TUNI) in CLIP models, a novel technique for identity inference that: 1) only utilizes text data to query the target model; and 2) eliminates the need for training shadow models.
  arXiv  Detail & Related papers  (2024-05-23T12:54:25Z)
• Is my Data in your AI Model? Membership Inference Test with Application to Face Images [18.402616111394842]
  This article introduces the Membership Inference Test (MINT), a novel approach that aims to empirically assess if given data was used during the training of AI/ML models. We propose two MINT architectures designed to learn the distinct activation patterns that emerge when an Audited Model is exposed to data used during its training process. Experiments are carried out using six publicly available databases, comprising over 22 million face images in total.
  arXiv  Detail & Related papers  (2024-02-14T15:09:01Z)
• FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction [49.510163437116645]
  Click-through rate (CTR) prediction plays as a core function module in personalized online services. Traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality. Pretrained Language Models(PLMs) has given rise to another paradigm, which takes as inputs the sentences of textual modality. We propose to conduct Fine-grained feature-level ALignment between ID-based Models and Pretrained Language Models(FLIP) for CTR prediction.
  arXiv  Detail & Related papers  (2023-10-30T11:25:03Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation [3.7315964084413173]
  We propose an adversarial learning framework that deals with the privacy-utility tradeoff problem under two conditions. Under data-type ignorant conditions, the privacy mechanism provides a one-hot encoding of categorical features, representing exactly one class. Under data-type aware conditions, the categorical variables are represented by a collection of scores, one for each class.
  arXiv  Detail & Related papers  (2022-05-04T08:40:15Z)
• Exploring Multi-Modal Representations for Ambiguity Detection & Coreference Resolution in the SIMMC 2.0 Challenge [60.616313552585645]
  We present models for effective Ambiguity Detection and Coreference Resolution in Conversational AI. Specifically, we use TOD-BERT and LXMERT based models, compare them to a number of baselines and provide ablation experiments. Our results show that (1) language models are able to exploit correlations in the data to detect ambiguity; and (2) unimodal coreference resolution models can avoid the need for a vision component.
  arXiv  Detail & Related papers  (2022-02-25T12:10:02Z)
• Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets [56.018551958004814]
  This paper addresses the task of generating fluent descriptions by training on a non-uniform combination of data sources. Large-scale datasets with noisy image-text pairs provide a sub-optimal source of supervision. We propose to leverage and separate semantics and descriptive style through the incorporation of a style token and keywords extracted through a retrieval component.
  arXiv  Detail & Related papers  (2021-11-24T19:00:05Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.