"Show Me You Comply... Without Showing Me Anything": Zero-Knowledge Software Auditing for AI-Enabled Systems

• URL: http://arxiv.org/abs/2510.26576v1
• Date: Thu, 30 Oct 2025 15:03:32 GMT
• Title: "Show Me You Comply... Without Showing Me Anything": Zero-Knowledge Software Auditing for AI-Enabled Systems
• Authors: Filippo Scaramuzza, Renato Cordeiro Ferreira, Tomaz Maia Suller, Giovanni Quattrocchi, Damian Andrew Tamburri, Willem-Jan van den Heuvel,
• Abstract summary: This paper introduces ZKMLOps, a novel MLOps verification framework.<n>It operationalizes Zero-Knowledge Proofs (ZKPs)-cryptographic protocols allowing a prover to convince a verifier that a statement is true.<n>We evaluate the framework's practicality through a study of regulatory compliance in financial risk auditing.
• Score: 2.2981698355892686
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The increasing exploitation of Artificial Intelligence (AI) enabled systems in critical domains has made trustworthiness concerns a paramount showstopper, requiring verifiable accountability, often by regulation (e.g., the EU AI Act). Classical software verification and validation techniques, such as procedural audits, formal methods, or model documentation, are the mechanisms used to achieve this. However, these methods are either expensive or heavily manual and ill-suited for the opaque, "black box" nature of most AI models. An intractable conflict emerges: high auditability and verifiability are required by law, but such transparency conflicts with the need to protect assets being audited-e.g., confidential data and proprietary models-leading to weakened accountability. To address this challenge, this paper introduces ZKMLOps, a novel MLOps verification framework that operationalizes Zero-Knowledge Proofs (ZKPs)-cryptographic protocols allowing a prover to convince a verifier that a statement is true without revealing additional information-within Machine-Learning Operations lifecycles. By integrating ZKPs with established software engineering patterns, ZKMLOps provides a modular and repeatable process for generating verifiable cryptographic proof of compliance. We evaluate the framework's practicality through a study of regulatory compliance in financial risk auditing and assess feasibility through an empirical evaluation of top ZKP protocols, analyzing performance trade-offs for ML models of increasing complexity.

Related papers

• 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)
• CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks [54.04030169323115]
  We introduce CREDIT, a certified ownership verification against Model Extraction Attacks (MEAs)<n>We quantify the similarity between DNN models, propose a practical verification threshold, and provide rigorous theoretical guarantees for ownership verification based on this threshold.<n>We extensively evaluate our approach on several mainstream datasets across different domains and tasks, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-23T23:36:25Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• Generation of Programmatic Rules for Document Forgery Detection Using Large Language Models [10.32461766065764]
  Document forgery poses a growing threat to legal, economic, and governmental processes.<n>Existing plausibility checks are manually implemented by software engineers, which is time-consuming.<n>Recent advances in code generation with large language models (LLMs) offer new potential for automating and scaling the generation of these checks.
  arXiv  Detail & Related papers  (2025-12-22T10:08:25Z)
• AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning (AIRS) Framework [31.261980405052938]
  Assurance for artificial intelligence (AI) systems remains fragmented across software supply-chain security, adversarial machine learning, and governance documentation.<n>This paper introduces the AI Risk Scanning (AIRS) Framework, a threat-model-based, evidence-generating framework designed to operationalize AI assurance.
  arXiv  Detail & Related papers  (2025-11-16T16:10:38Z)
• Confidentiality-Preserving Verifiable Business Processes through Zero-Knowledge Proofs [0.0]
  This paper introduces a zero-knowledge proof (ZKP)-based approach for the verifiable execution of business processes.<n>Our approach supports chained verifiable computations through proof compositions.
  arXiv  Detail & Related papers  (2025-09-24T16:32:48Z)
• Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned [45.44933002008943]
  This white paper presents the T"UV AUSTRIA Trusted AI framework.<n>It is an end-to-end audit catalog and methodology for assessing and certifying machine learning systems.<n>Building on three pillars - Secure Software Development, Functional Requirements, and Ethics & Data Privacy - it translates the high-level obligations of the EU AI Act into specific, testable criteria.
  arXiv  Detail & Related papers  (2025-09-08T17:52:08Z)
• Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs [1.7723990552388873]
  Zero-Knowledge Proofs (ZKPs) offer a cryptographic solution that enables provers to demonstrate, through verified computations, adherence to set requirements without revealing sensitive model details or data.<n>We identify five key properties (non-interactivity, transparent setup, standard representations, succinctness, and post-quantum security) critical for their application in AI validation and verification pipelines.
  arXiv  Detail & Related papers  (2025-05-26T15:39:11Z)
• Trustless Audits without Revealing Data or Models [49.23322187919369]
  We show that it is possible to allow model providers to keep their model weights (but not architecture) and data secret while allowing other parties to trustlessly audit model and data properties. We do this by designing a protocol called ZkAudit in which model providers publish cryptographic commitments of datasets and model weights.
  arXiv  Detail & Related papers  (2024-04-06T04:43:06Z)
• Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities [1.3225694028747144]
  We propose a Coordinated Flaw Disclosure framework tailored to the complexities of machine learning (ML) issues. Our framework introduces innovations such as extended model cards, dynamic scope expansion, an independent adjudication panel, and an automated verification process. We argue that CFD could significantly enhance public trust in AI systems.
  arXiv  Detail & Related papers  (2024-02-10T20:39:04Z)
• A General Framework for Verification and Control of Dynamical Models via Certificate Synthesis [54.959571890098786]
  We provide a framework to encode system specifications and define corresponding certificates. We present an automated approach to formally synthesise controllers and certificates. Our approach contributes to the broad field of safe learning for control, exploiting the flexibility of neural networks.
  arXiv  Detail & Related papers  (2023-09-12T09:37:26Z)
• Relational Action Bases: Formalization, Effective Safety Verification, and Invariants (Extended Version) [67.99023219822564]
  We introduce the general framework of relational action bases (RABs) RABs generalize existing models by lifting both restrictions. We demonstrate the effectiveness of this approach on a benchmark of data-aware business processes.
  arXiv  Detail & Related papers  (2022-08-12T17:03:50Z)
• Trustworthy Artificial Intelligence and Process Mining: Challenges and Opportunities [0.8602553195689513]
  We show that process mining can provide a useful framework for gaining fact-based visibility to AI compliance process execution. We provide for an automated approach to analyze, remediate and monitor uncertainty in AI regulatory compliance processes.
  arXiv  Detail & Related papers  (2021-10-06T12:50:47Z)

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.