SPATA: Systematic Pattern Analysis for Detailed and Transparent Data Cards

2025-09-30

AI Summary

How can external AI/ML models be robustly verified and interpretably assessed for privacy-sensitive applications—without accessing original training or test data? This paper proposes SPATA, a statistical pattern projection framework that maps tabular data into domain-agnostic, discretized, deterministic pattern representations. By implicitly modeling decision boundaries via these patterns, SPATA avoids exposing sensitive raw data. It establishes the first deterministic verification framework enabling both quantitative robustness analysis and interpretable report generation without requiring original datasets. Its core innovation lies in substituting individual instances with reproducible statistical patterns—thereby preserving data privacy while enabling reliable feature attribution and auditability of model behavior. Experiments demonstrate that SPATA significantly enhances transparency, verifiability, and trustworthiness of AI systems under strict privacy constraints.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: Safety and Robustness
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Due to the susceptibility of Artificial Intelligence (AI) to data perturbations and adversarial examples, it is crucial to perform a thorough robustness evaluation before any Machine Learning (ML) model is deployed. However, examining a model's decision boundaries and identifying potential vulnerabilities typically requires access to the training and testing datasets, which may pose risks to data privacy and confidentiality. To improve transparency in organizations that handle confidential data or manage critical infrastructure, it is essential to allow external verification and validation of AI without the disclosure of private datasets. This paper presents Systematic Pattern Analysis (SPATA), a deterministic method that converts any tabular dataset to a domain-independent representation of its statistical patterns, to provide more detailed and transparent data cards. SPATA computes the projection of each data instance into a discrete space where they can be analyzed and compared, without risking data leakage. These projected datasets can be reliably used for the evaluation of how different features affect ML model robustness and for the generation of interpretable explanations of their behavior, contributing to more trustworthy AI.

Problem

• Evaluating AI robustness without exposing private training data
• Converting tabular datasets to secure statistical pattern representations
• Enabling external validation of ML models while preserving confidentiality

Innovation

• Converts datasets to domain-independent statistical patterns
• Projects data instances into discrete space for analysis
• Enables ML robustness evaluation without data leakage