Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study

• URL: http://arxiv.org/abs/2608.03172v3
• Date: Thu, 13 Aug 2026 03:45:55 GMT
• Title: Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
• Abstract summary: Structure-preserving de-identification replaces protected health information with realistic same-type surrogates.<n>Can downstream PHI detectors still find the surrogate?<n>Across 11 detectors, 7 benchmarks, and 7 languages (1,750 documents), recall on masked spans moves from 76.1% to 74.9%.<n>A redaction floor and an open-source surrogate baseline indicate the effect is a property of well-formed substitution, not of one tool.
• Score: 2.7278797508895316
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structure-preserving de-identification replaces protected health information (PHI) with realistic same-type surrogates -- "Anna S." becomes "Maria S.", not [NAME] -- so that clinical text stays fluent and downstream tools keep working. But this only helps if the substitution does not itself corrupt the signal those tools rely on. We ask a narrow, testable question: on the spans a de-identifier actually masks, can downstream PHI detectors still find the surrogate? We introduce a paired, multi-detector evaluation protocol that (i) scores utility only on masked spans, decoupling coverage from utility; (ii) uses equivalence testing (TOST) rather than null-hypothesis significance testing, which is uninformative at our sample size (57k paired spans); and (iii) builds a surrogate-failure typology separating fixable generator defects from intrinsic detector limits. Across 11 detectors, 7 benchmarks, and 7 languages (1,750 documents), recall on masked spans moves from 76.1% to 74.9% -- a change our equivalence test shows is statistically equivalent to zero within a +/-2-point margin (p ~ 3e-9), with detector ranking preserved. The residual loss does not reflect detectors getting worse at PHI: it concentrates in malformed and out-of-distribution surrogates (truncation Chicago -> Illino, salience loss Cedars-Sinai -> Vidant). A redaction floor and an open-source surrogate baseline indicate the effect is a property of well-formed substitution, not of one tool. We release the evaluation subsets, scoring code, and an interactive dashboard at https://custodianai.pages.dev so the protocol can audit any structure-preserving transform.

Related papers

• Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data [0.5213778368155993]
  DIFFINT is an autoencoder whose latent bottleneck is structured as a set of soft, axis-aligned interval memberships.<n>It is the only interpretable detector in the statistically-tied leading cluster of seven methods.
  arXiv  Detail & Related papers  (2026-09-03T14:05:27Z)
• Label-Free Parkinson's Disease Screening from Face and Voice through Mechanistic Interpretability [4.241413288920499]
  Parkinson's disease (PD) is the second most common neurodegenerative disorder.<n>We propose a label-free face-plus-voice PD screen built entirely on frozen pretrained encoders.<n>We show that a synthetic-degradation CAA detector works when the cosine similarity between the synthetic and real disease directions exceeds zero.
  arXiv  Detail & Related papers  (2026-08-10T00:43:57Z)
• What the Detector Can See: Evaluating CPS Anomaly Detectors Independently of the Decision Rule [6.145872664954402]
  Anomaly detectors are often the last line of defense for cyber-physical systems.<n>These detectors are usually compared using precision, recall, or F1 at a single operating point.<n>We treat a CPS anomaly detector as a two-stage pipeline: Stage 1 maps observations to residuals, and Stage 2 maps residuals to alarms.<n>We evaluate five detectors across three CPS benchmarks: SWaT, WADI, and HAI.
  arXiv  Detail & Related papers  (2026-08-03T19:35:00Z)
• Level, Sharpness, and Corpus: Why Zero-Shot OOD Detector Rankings Do Not Transfer [36.02174685737611]
  We find that detector rankings reverse across deployments, every detector exceeds $80%$ FPR95 on at least one domain, and the preferred detector depends on both the in-distribution data and the underlying VLM.<n>We introduce the Complementary Evidence Guard (CEG), a detector-agnostic wrapper that preserves complementary evidence through a non-compensatory fusion of the base detector, level, and sharpness.
  arXiv  Detail & Related papers  (2026-07-29T08:00:49Z)
• Spatially Selective Self-Training for Unsupervised Building Change Detection [8.884818023657276]
  Unsupervised building change detection aims to learn building-change masks from unlabeled bi-temporal remote sensing images.<n>SST-CD is a spatially selective self-training framework that reformulates fully label-free building change detection as end-to-end detector learning.<n>Experiments show that SST-CD achieves F1 scores of 83.08%, 91.69%, and 86.60%, respectively, outperforming existing unsupervised and label-free baselines.
  arXiv  Detail & Related papers  (2026-06-09T12:31:16Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• Unsupervised Domain Shift Detection with Interpretable Subspace Attribution [48.553902624178995]
  Domain shifts are subtle differences in the probability distributions of datasets.<n>We identify these shifts using an algorithm designed to detect localised density anomalies in high-dimensional feature spaces.<n>We trace the domain shift to a small set of features, making the shift interpretable.
  arXiv  Detail & Related papers  (2026-05-15T12:58:00Z)
• Are Benchmark Tests Strong Enough? Mutation-Guided Diagnosis and Augmentation of Regression Suites [49.16055123488827]
  Insufficiently strong test suites can admit plausible yet semantically incorrect patches, inflating reported success rates.<n>We introduce STING, a framework for targeted test augmentation that uses semantically altered program variants as diagnostic stressors.<n>STING produces 1,014 validated tests spanning 211 instances and increases patch-region line and branch coverage by 10.8% and 9.5%.
  arXiv  Detail & Related papers  (2026-04-02T01:13:40Z)
• Universal Transformation of One-Class Classifiers for Unsupervised Anomaly Detection [51.73001988341294]
  Anomaly detection is typically formulated as a one-class classification problem.<n>We present a dataset folding method that transforms an arbitrary one-class classifier-based anomaly detector into a fully unsupervised method.
  arXiv  Detail & Related papers  (2026-02-13T16:54:12Z)
• AI-Generated Text is Non-Stationary: Detection via Temporal Tomography [22.211451973387796]
  We introduce Temporal Discrepancy Tomography (TDT), a novel detection paradigm that preserves positional information by reformulating detection as a signal processing task.<n>On the RAID benchmark, TDT achieves 0.855 AUROC (7.1% improvement over the best baseline)<n>Our work establishes non-stationarity as a fundamental characteristic of AI-generated text and demonstrates that preserving temporal dynamics is essential for robust detection.
  arXiv  Detail & Related papers  (2025-08-03T13:43:34Z)
• Group-Adaptive Threshold Optimization for Robust AI-Generated Text Detection [58.419940585826744]
  We introduce FairOPT, an algorithm for group-specific threshold optimization for probabilistic AI-text detectors.<n>We partitioned data into subgroups based on attributes (e.g., text length and writing style) and implemented FairOPT to learn decision thresholds for each group to reduce discrepancy.<n>Our framework paves the way for more robust classification in AI-generated content detection via post-processing.
  arXiv  Detail & Related papers  (2025-02-06T21:58:48Z)
• Can AI-Generated Text be Reliably Detected? [50.95804851595018]
  Large Language Models (LLMs) perform impressively well in various applications.<n>The potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their responsible use.<n>We stress-test the robustness of these AI text detectors in the presence of an attacker.
  arXiv  Detail & Related papers  (2023-03-17T17:53:19Z)
• Mitigating the Mutual Error Amplification for Semi-Supervised Object Detection [92.52505195585925]
  We propose a Cross Teaching (CT) method, aiming to mitigate the mutual error amplification by introducing a rectification mechanism of pseudo labels. In contrast to existing mutual teaching methods that directly treat predictions from other detectors as pseudo labels, we propose the Label Rectification Module (LRM)
  arXiv  Detail & Related papers  (2022-01-26T03:34:57Z)

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.