paper-with-me

홈 › Papers

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation

2026-05-16 · Osama Zafar, Alexander Nemecek, Yiqian Zhang, Wenbiao Li, Debargha Ganguly, Vikash Singh, Vipin Chaudhary, Erman Ayday arxiv

Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individuals. We introduce a Privacy Policy Enforcement (PPE) framework using dual one-class density estimators with fused text embeddings and a calibrated abstain region for out-of-distribution inputs. Using an axis-stratified, multi-LLM synthetic data pipeline across medicine, finance, and law, we found that traditional Gaussian Mixture baselines fail on borderline-safe stress tests by focusing on linguistic register rather than content. Our proposed T3+OCSVM detector, trained on safe and borderline-safe data, achieves a borderline AUROC of 0.93+ while reducing false positives by 44-55 percentage points and maintaining millisecond latency. Compared to supervised MLP classifiers or 14B-parameter LLM judges, our framework offers superior operational suitability, as the former suffers from high abstention rates and the latter from latency and calibration issues. This methodology provides a robust stress-testing standard for any synthetic-data-trained classifier.

📄 PDF Abstract BibTeX arXiv:2605.17034

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails

2026-05-29 · Yan Wang, Zhixuan Chu, Zihao Xue, Zhen Bi 외 arxiv

Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful enforcement: a model may recognize a har…

LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance

2025-05-22 · Yu Wang, Cailing Cai, Zhihua Xiao, Peifung E. Lam

Large language models (LLMs) are increasingly applied in fields such as finance, education, and governance due to their ability to generate human-like text and adapt to specialized tasks. However, their widespread adopti…

Autoformalization of Agent Instructions into Policy-as-Code

2026-06-25 · Adam Mondl, Matthew Maisel, John H. Brock arxiv

Agent safety in high-stakes domains requires formal policy enforcement, but most existing approaches either rely on probabilistic guardrails (fine-tuned classifiers, prompt-based steering) that offer no formal guarantees…

A Privacy-Preserving Cloud Architecture for Distributed Machine Learning at Scale

2025-12-11 · Vinoth Punniyamoorthy, Ashok Gadi Parthi, Mayilsamy Palanigounder, Ravi Kiran Kodali 외 arxiv

Distributed machine learning systems require strong privacy guarantees, verifiable compliance, and scalable deployment across heterogeneous and multi-cloud environments. This work introduces a cloud-native privacy-preser…

Reinforcement LearningFederated Learning

OpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language Models

2025-10-22 · Thomas Wang, Haowen Li arxiv

As large language models (LLMs) are increasingly integrated into real-world applications, ensuring their safety, robustness, and privacy compliance has become critical. We present OpenGuardrails, the first fully open-sou…

Text Generation