Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing

• URL: http://arxiv.org/abs/2604.24203v1
• Date: Mon, 27 Apr 2026 09:07:15 GMT
• Title: Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing
• Abstract summary: We propose em Agentic Witnessing, a framework that moves verification from execution to reasoning.<n>The system is composed of three agents: a Verifier (who wants to check properties of a dataset), a Prover (who owns the dataset) and an Auditor (that inspects the dataset).<n>By isolating an LLM-based Auditor within a Trusted Execution Environment (TEE), the system enables the Verifier to query a Prover's private data via simple queries, without exposing the raw dataset.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Auditing the semantic properties of proprietary data creates a fundamental tension: verification requires transparent access, while proprietary rights demand confidentiality. While Zero-Knowledge Proofs (ZKPs) ensure privacy, they are typically limited to precise algebraic constraints and are ill-suited for verifying qualitative, unstructured properties, such as the logic within a codebase. We propose {\em Agentic Witnessing}, a framework that moves verification from attested execution to {\em attested reasoning}. The system is composed of three agents: a Verifier (who wants to check properties of a dataset), a Prover (who owns the dataset) and an Auditor (that inspects the dataset). The Verifier is allowed to ask a limited number of simple binary true/false questions to the auditor. By isolating an LLM-based Auditor within a Trusted Execution Environment (TEE), the system enables the Verifier to query a Prover's private data via simple Boolean queries, without exposing the raw dataset. The Auditor uses the Model Context Protocol (MCP) to dynamically inspect the target dataset, producing a yes/no verdict accompanied by a cryptographic transcript: a signed hash chain binding the reasoning trace to both the original dataset and the TEE's hardware root of trust. We demonstrate this architecture by automating the artifact evaluation process for 21 peer-reviewed computer science papers with released codebases on GitHub (e.g. Does the codebase implement the system described in the paper?). We verified five high-level properties of these codebases described in the corresponding publications, treating the source code as private. Our results show that TEE-enabled agentic auditing provides a mechanism for privacy-preserving oversight, effectively decoupling qualitative verification from the need for data disclosure.

Related papers

• Zero-Knowledge Predicate Proofs Between AI Agents: A Measured, Cross-Protocol Gateway and the Source-Integrity Gap [0.0]
  Multi-agent AI platforms move quickly from staging to production, but the way agents establish trust remains rudimentary.<n>We take provable data minimisation between agents from proposal to running system.<n>A 32-bit threshold predicate proves in 6.2 ms and verifies in 1.0 ms with a 608-byte Bulletproofs proof.
  arXiv  Detail & Related papers  (2026-08-30T23:16:17Z)
• Formal Verification of Agentic Systems over Operational Data [59.98246281888422]
  Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world where they act on persistent operational data.<n>Existing approaches do not provide such system-level guarantees.<n>We study here the verification of agentic systems comprising a single LLM and a tool orchestration harness over relational operational data.
  arXiv  Detail & Related papers  (2026-08-04T13:01:30Z)
• Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data [56.86147283213652]
  We present a customizable empirical auditing framework designed to detect and explain data disclosures.<n>Our framework introduces a mechanism to distinguish between "true disclosures"-where the system directly reproduces a user's information-and "phantom disclosures"-where the system incidentally generates a user's data.
  arXiv  Detail & Related papers  (2026-06-15T16:54:02Z)
• Ontological Knowledge Blocks: Executable Compliance and Profile-Based Validation for Trustworthy AI Systems [0.0]
  This paper introduces Ontological Knowledge Blocks (OKBs), a programmable governance infrastructure that compiles regulatory obligations into machine-checkable constraints.<n>A deterministic regulatory compiler translates structured Intermediate Representation (IR) records into composable KB modules, enabling profile-based governance provenance.<n>Results demonstrate profile-sensitive validation, strictly additive violation accumulation, SHACL validation reconfiguration latency between 12.6 ms and 100.3 ms, and profile equivalence testing confirming Combined as the strictly most comprehensive profile.
  arXiv  Detail & Related papers  (2026-05-22T07:14:31Z)
• Making AI-Assisted Grant Evaluation Auditable without Exposing the Model [0.0]
  We propose a TEE-based architecture that helps reconcile requirements through remote attestation.<n>The architecture allows an external verifier to check which model, rubric, prompt template, and input representation were used.<n>We position the design relative to confidential AI inference, attestable AI audits, zero-knowledge machine learning, algorithmic accountability, and AI-assisted peer review.
  arXiv  Detail & Related papers  (2026-04-28T04:10:04Z)
• AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation [71.49152943451328]
  We introduce a benchmark AJ-Bench to evaluate Agent-as-a-Judge across three domains-search, data systems, and graphical user interfaces-comprising 155 tasks and 516 annotated trajectories.<n>Experiments demonstrate consistent performance gains over LLM-as-a-Judge baselines, while also revealing substantial open challenges in agent-based verification.
  arXiv  Detail & Related papers  (2026-04-20T13:23:38Z)
• IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation [49.796717294455796]
  We present IMMACULATE, a practical auditing framework that detects economically motivated deviations.<n>IMMACULATE selectively audits a small fraction of requests using verifiable computation, achieving strong detection guarantees while amortizing cryptographic overhead.
  arXiv  Detail & Related papers  (2026-02-26T07:21:02Z)
• EigenAI: Deterministic Inference, Verifiable Results [3.231493128964671]
  EigenAI is a verifiable AI platform built on top of the EigenLayer restaking ecosystem.<n>It combines a deterministic large-language model (LLM) inference engine with a cryptoeconomically secured optimistic re-execution protocol.
  arXiv  Detail & Related papers  (2026-01-30T04:46:22Z)
• Document Data Matching for Blockchain-Supported Real Estate [2.9873162504735133]
  This work presents a system that integrates optical character recognition (OCR), natural language processing (NLP), and verifiable credentials (VCs) to automate document extraction, verification, and management.<n>The approach standardizes heterogeneous document formats into VCs and applies automated data matching to detect inconsistencies, while the blockchain provides a decentralized trust layer that reinforces transparency and integrity.<n>The proposed framework demonstrates the potential to streamline real estate transactions, strengthen stakeholder trust, and enable scalable, secure digital processes.
  arXiv  Detail & Related papers  (2025-12-30T20:30:48Z)
• RepoMark: A Data-Usage Auditing Framework for Code Large Language Models [16.976151053365385]
  We propose a novel data marking framework RepoMark to audit the data usage of code LLMs.<n>Our method enables auditors to verify whether their code has been used in training, while ensuring semantic preservation.<n>RepoMark achieves a detection success rate over 90% on small code repositories under a strict FDR guarantee of 5%.
  arXiv  Detail & Related papers  (2025-08-29T09:01:34Z)
• CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking [85.68235482145091]
  Large-scale speech datasets have become valuable intellectual property.<n>We propose a novel dataset ownership verification method.<n>Our approach introduces a clustering-based backdoor watermark (CBW)<n>We conduct extensive experiments on benchmark datasets, verifying the effectiveness and robustness of our method against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-03-02T02:02:57Z)
• Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning [58.57194301645823]
  Large language models (LLMs) are increasingly integrated into real-world personalized applications.<n>The valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries.<n>Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning or backdoor attacks.<n>We propose name for harmless' copyright protection of knowledge bases.
  arXiv  Detail & Related papers  (2025-02-10T09:15:56Z)
• OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs [59.836774258359945]
  OpenFactCheck is a framework for building customized automatic fact-checking systems.<n>It allows users to easily customize an automatic fact-checker and verify the factual correctness of documents and claims.<n>CheckerEVAL is a solution for gauging the reliability of automatic fact-checkers' verification results using human-annotated datasets.
  arXiv  Detail & Related papers  (2024-05-09T07:15:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.