Constraining the Commit Boundary: A DIO/ODI-Informed Authorization Guardrail for Agentic Entity Resolution

Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.

Les articles les plus proches

1. Proche Pas pertinent

   Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure

   Jun-Fei He, De-Ying Yu · 2026 · arXiv.org · preprint, non relu par les pairs · cité 4 fois · Pas encore résumé

   Résumé scientifique

   Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet existing security mechanisms -- such as identity and access management (IAM), policy engines, consensus protocols, and audit logs -- either enforce static, context-unaware permissions or merely record actions post-execution. This paper introduces the Sovereign Assurance Boundary (SAB), a certificate-bound runtime admission layer for autonomous execution authority. SAB intercepts agent proposals at an assurance airlock, compiles them into typed execution contracts $C$, and binds these contracts to cryptographic evi…

2. Proche Pas pertinent

   Partial Evidence Bench: Benchmarking Authorization-Limited Evidence in Agentic Systems

   Krti Tallam · 2026 · arXiv.org · preprint, non relu par les pairs · cité 5 fois · Pas encore résumé

   Résumé scientifique

   Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer that appears complete even though material evidence lies outside the caller's authorization boundary. This paper introduces Partial Evidence Bench, a deterministic benchmark for measuring that failure mode. The benchmark ships three scenario families -- due diligence, compliance audit, and security incident response -- with 72 tasks total, ACL-partitioned corpora, oracle complete answers, oracle authorized-view answers, oracle completeness judgments, and …

3. Proche Cité par cet article Pas pertinent

   Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents

   Igor Santos-Grueiro · 2026 · arXiv.org · preprint, non relu par les pairs · cité 24 fois · Pas encore résumé

   Résumé scientifique

   LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result. We study the commit boundary at which earlier authority evidence no longer authorizes a durable effect. We call this property commit-time authorization: a durable effect is authorized only if the witness that licensed its derived state remains fresh, causally prior, bound to the same effect, and eligible at commit time. We build a controlled-invalidation suite spanning browser, tool/API, and multi-agent workflows. The suite preserves the user goal and payload shape while invalidating the authority relation before d…

4. Proche Pas pertinent

   From Entity Resolution Anomalies to Reconstruction Failure Modes: A Taxonomic Note Following Minimum Viable Digital Identity Optimization (DIO)

   Daniel Beránek · 2026 · Zenodo (CERN European Organization for Nuclear Research) preprint · Résumé IA disponible

   Résumé scientifique

   This taxonomic note refines the vocabulary of Entity Resolution Anomalies developed in The Crisis of Entity Resolution in Heterogeneous AI Environments and follows the adversarial reduction introduced in Minimum Viable Digital Identity Optimization (DIO): From Adversarial Reduction to the Semantic Field Dynamics of Digital Identity. It proposes a non-exclusive, multi-level diagnostic taxonomy of Reconstruction Failure Modes. The taxonomy distinguishes four analytical domains: Referential Reconstruction Failures, Semantic Coherence Failures, Temporal Reconstruction Failures, and Contextual Adequacy Failures. Referential failures include Entity Substitution, Merge Failure, Split Failure, and E…

5. Proche Pas pertinent

   Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure

   Krti Tallam · 2026 · arXiv.org · preprint, non relu par les pairs · cité 11 fois · Pas encore résumé

   Résumé scientifique

   The security discussion around agentic AI focuses heavily on prompt injection. This paper argues that multi-agent systems also create a distinct authorization problem: maintaining authorization invariants as non-human principals retrieve data, delegate tasks, and synthesize results across changing boundaries. We call this problem authorization propagation. It is not reducible to prompt injection and is not fully addressed by classical access-control models such as RBAC, ABAC, or ReBAC. The paper formalizes authorization propagation as a workflow-level property, identifies three sub-problems (transitive delegation, aggregation inference, and temporal validity), and derives seven structural re…

6. Proche Pas pertinent

   Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI

   Amjad Ibrahim, Yong Li · 2026 · arXiv.org · preprint, non relu par les pairs · cité 4 fois · Pas encore résumé

   Résumé scientifique

   As AI systems evolve from passive models into autonomous active agents capable of initiating actions, collaborating, and delegating tasks, the traditional boundaries of software systems blur. Traditional authorization and delegation frameworks, built around fixed principals, explicit requests, and static scopes, are insufficient to govern agentic systems. Agentic AI demands richer authorization semantics: agents must inherit and delegate permissions, act under time-limited authority, and coordinate through shared protocols. Existing Identity and Access Management (IAM) systems fail to fully capture this notion of agency, lacking mechanisms for recursive delegation, contextual boundaries, and…

7. Proche Pas pertinent

   Compliance-as-Code for AI-Driven Identity Systems: Clause-to-Control Traceability and Machine-Readable Evidence

   L. Nweke, P. Yeng · 2026 · IEEE Access · Pas encore résumé

   Résumé scientifique

   Artificial intelligence (AI)-driven identity (ID) systems (document onboarding, wallet-based credential presentation, fraud/risk scoring) increasingly face regulatory obligations requiring demonstrable accountability, traceability, and technical documentation. Yet current compliance practice remains predominantly document-centric and manual, making it difficult to keep evidence synchronized with rapidly evolving systems and models. We present a compliance-as-code approach for AI-driven ID workflows that: 1) maintains clause-to-control traceability under policy/configuration evolution; 2) treats evidence completeness as an enforceable property via fixed monitoring-window semantics (silence is…

8. Proche Pas pertinent

   Digital Identity for Agentic Systems: Toward a Portable Authorization Standard for Autonomous Agents

   Partha Madhira · 2026 · arXiv.org · preprint, non relu par les pairs · Pas encore résumé

   Résumé scientifique

   Enterprise AI is shifting from copilots to autonomous agents capable of executing workflows, negotiating outcomes, and making decisions with limited human oversight. As these systems extend across organizational boundaries, identity alone is insufficient: an agent's authority must also be explicit, constrained, auditable, revocable, and consistently interpretable by independent receivers. This paper analyzes representative enterprise use cases in insurance claims processing and supply chain integrity to surface structural gaps in existing identity and access models. It proposes a portable authorization model for autonomous agents based on issuer-authored authorization payloads, typed constra…

Les travaux antérieurs sur lesquels il s’appuie

1. Apparenté Pas pertinent

   From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions

   Meng-Rong Wu, Lin Wang, Yong Zhang et al. · 2026 · cité 2 fois · Pas encore résumé

   Résumé scientifique

   AI agents increasingly propose actions with external consequences, including financial transfers, infrastructure changes, software deployments, disclosures, and physical actuation. Authorization engines, policy languages, runtime monitors, provenance mechanisms, and agent guardrails provide important foundations, but do not necessarily define a common semantic contract for the final transition from a particular candidate action to execution authority. We specify EBL-Core, an execution-boundary conformance profile for deciding whether one canonical, fully materialized AI-generated candidate may receive action-scoped execution authority under explicit conditions. It binds a structured intent o…

2. Apparenté Pas pertinent

   AgenticER: the next frontier in Entity Resolution

   George Papadakis, Panos Korovesis, Manolis Koubarakis et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 1 fois · Pas encore résumé

   Résumé scientifique

   Entity Resolution (ER) is a fundamental problem in data management, playing a critical role in tasks like data cleaning and knowledge graph construction. The existing ER approaches range from traditional rule-based to deep learning techniques and LLM-based methods, but typically operate under a ``passive paradigm'', as duplicates are detected through static, one-shot similarity computations. Such approaches fail to capture the inherently uncertain and context-dependent nature of real-world ER tasks, especially in data lakes with streaming content in heterogeneous formats such as CSV files, JSON files, RDF dumps, and free text. In such settings, resolving ambiguity often requires iterative ev…

3. Apparenté Pas pertinent

   CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls

   Chris Zheng, Yang Geng · 2026 · cité 4 fois · Pas encore résumé

   Résumé scientifique

   LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, individually correct security mechanisms do not necessarily compose into an end-to-end secure system: security-critical context may be dropped, widened, rebound, or reinterpreted as actions cross component boundaries. We identify this failure mode as security-context discontinuity and introduce CONTINUITY, a framework for verifiable composition of agent security controls. CONTINUITY models each component with an assume-guarantee contract and carries authenticated security context across transitions using signed root grants, provenance commitments,…

4. Apparenté Pas pertinent

   From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI

   Hongyin Zhu, Jinming Liang, Mengjun Hou et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 1 fois · Pas encore résumé

   Résumé scientifique

   Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how active business scenarios reshape that space for the event at hand -- producing decisions that are fluent but ungrounded and carrying no audit trail. We present LOM-action, which equips enterprise AI with \emph{event-driven ontology simulation}: business events trigger scenario conditions encoded in the enterprise ontology~(EO), which drive deterministic graph mutations in an isolated sandbox, evolving a working copy of the subgraph into the scenario-valid simulation graph $G_{\text{sim}}$; all decisions are derived exclusively from this evolve…

5. Apparenté Utilisé en profondeur par cet article Pas pertinent

   An Overview of End-to-End Entity Resolution for Big Data

   V. Christophides, Vasilis Efthymiou, Themis Palpanas et al. · 2020 · ACM Computing Surveys · cité 300 fois · Pas encore résumé

   Résumé scientifique

   One of the most critical tasks for improving data quality and increasing the reliability of data analytics is Entity Resolution (ER), which aims to identify different descriptions that refer to the same real-world entity. Despite several decades of research, ER remains a challenging problem. In this survey, we highlight the novel aspects of resolving Big Data entities when we should satisfy more than one of the Big Data characteristics simultaneously (i.e., Volume and Velocity with Variety). We present the basic concepts, processing steps, and execution strategies that have been proposed by database, semantic Web, and machine learning communities in order to cope with the loose structurednes…