TL;DR
This paper presents a layered security architecture for enterprise retrieval-augmented AI systems that ensures tenant data confidentiality and compliance, addressing limitations of traditional relevance-based retrieval methods.
Contribution
It introduces a server-side, policy-aware layered architecture with ABAC gating for multitenant security in enterprise AI retrieval systems, validated through an open-source implementation.
Findings
ABAC gating effectively prevents cross-tenant data leakage.
The proposed architecture introduces negligible performance overhead.
The implementation demonstrates practical enforcement of security policies in enterprise AI.
Abstract
Retrieval-Augmented Generation (RAG) and agentic AI systems are increasingly prevalent in enterprise AI deployments. However, real enterprise environments introduce challenges largely absent from academic treatments and consumer-facing APIs: multiple tenants with heterogeneous data, strict access-control requirements, regulatory compliance, and cost pressures that demand shared infrastructure. A fundamental problem underlies existing RAG architectures in these settings: retrieval systems rank documents by relevance--whether through semantic similarity, keyword matching, or hybrid approaches--not by authorization, so a query from one tenant can surface another tenant's confidential data simply because it scores highest. We formalize this gap and analyze additional shortcomings--including tool-mediated disclosure, context accumulation across turns, and client-side orchestration…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
