SEAL-Tag: Self-Tag Evidence Aggregation with Probabilistic Circuits for PII-Safe Retrieval-Augmented Generation

Computer Science > Cryptography and Security [Submitted on 18 Mar 2026] SEAL-Tag: Self-Tag Evidence Aggregation with Probabilistic Circuits for PII-Safe Retrieval-Augmented Generation Jin Xie, Songze Li, Guang Cheng Retrieval-Augmented Generation (RAG) systems introduce a critical vulnerability: contextual leakage, where adversaries exploit instruction-following to exfiltrate Personally Identifiable Information (PII) via adaptive extraction. Current defenses force a rigid trade-off between semantic utility and latency. We present SEAL-Tag, a privacy-preserving runtime environment that resolves this via a Verify-then-Route paradigm. SEAL-Tag introduces the SEAL-Probe protocol, transforming auditing into a structured tool-use operation where the model generates a verifiable PII-Evidence Table (PET) alongside its draft. To adjudicate this evidence, we employ a Probabilistic Circuit (PC) that enforces verifiable logical constraints for robust decision-making. To overcome the privacy "Cold Start" problem, we introduce the S0--S6 Anchored Synthesis Pipeline, generating high-fidelity, provenanced RAG interactions. We pair this with a Two-Stage Curriculum that first optimizes for entity detection before aligning the model to the rigorous audit protocol. Our evaluation demonstrates that SEAL-Tag establishes a new Pareto frontier, reducing adaptive leakage by over 8\times while matching the utility and speed of unsafe baselines. Comments: 13 pages, 5 figures Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2603.17292 [cs.CR]   (or arXiv:2603.17292v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.17292 Focus to learn more Submission history From: Jin Xie [view email] [v1] Wed, 18 Mar 2026 02:40:54 UTC (199 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)