mlsanityData to 14 Oct 2026

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments

arXiv 2506.23706 ↗First posted 30 Jun 2025cs.AI cs.CL cs.CRcited by 8

Not on the map. Why?

Abstract (arXiv)

Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits, which run inside Trusted Execution Environments and enable users to verify interaction with a compliant AI model. Our work protects sensitive data even when model provider and auditor do not trust each other. This addresses verification challenges raised in recent AI governance frameworks. We build a prototype demonstrating feasibility on typical audit benchmarks against Llama-3.1.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 25 of its 59 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

25 of 59 references.

References · 25

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  2. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  3. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  4. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  5. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
  6. 2015Teaching Machines to Read and Comprehendcited by 1,049
  7. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  8. 2017The NarrativeQA Reading Comprehension Challengecited by 597
  9. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 384
  10. 2020Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claimscited by 165
  11. 2024Stealing Part of a Production Language Modelcited by 159
  12. 2024AI Sandbagging: Language Models can Strategically Underperform on Evaluationscited by 145
13 more
  1. 2023Auditing large language models: a three-layered approachcited by 137
  2. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 135
  3. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126
  4. 2024Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Modelscited by 122
  5. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  6. 2023The Gradient of Generative AI Release: Methods and Considerationscited by 63
  7. 2024COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Actcited by 24
  8. 2022Machine Learning with Confidential Computing: A Systematization of Knowledgecited by 15
  9. 2024Auditing of AI: Legal, Ethical and Technical Approachescited by 10
  10. 2022Actionable Guidance for High-Consequence AI Risk Management: Towards Standards Addressing AI Catastrophic Riskscited by 7
  11. 2025Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryptioncited by 7
  12. 2024Heckler: Breaking Confidential VMs with Malicious Interruptscited by 4
  13. 2025Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptographycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026Proof-of-Guardrail in AI Agents and What (Not) to Trust from Itcited by 4
  2. 2026Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demandscited by 2
  3. 2026Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofscited by 2
  4. 2025TRUST: A Decentralized Framework for Auditing Large Language Model Reasoningcited by 1
  5. 2026Computational Compliance for AI Regulation: Blueprint for a New Research Domaincited by 1
  6. 2026Making AI-Assisted Grant Evaluation Auditable without Exposing the Modelcited by 0
  7. 2026Privacy-Preserving AI Verification via Minimal Information Disclosurecited by 0
  8. 2026SoK: Decentralized Agent Economic Infrastructurecited by 0