Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
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
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
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
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 LearningOpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language Models
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