Overview

Black-box model auditing studies what can be verified about an AI system when its weights, training data, or internal processes are inaccessible. Auditors use statistical tests and membership inference, active or sequential query selection, counterfactual and causal probes, behavioral fingerprints, and sometimes cryptographic verification to examine privacy, fairness, safety, robustness, explanations, and model identity. These methods are applied to settings from hosted language-model APIs and recommendation systems to scientific predictors, often using controlled benchmarks, matched interventions, and repeated trials. A central tension is that limited or manipulable outputs can conceal rare failures and make latent properties hard to establish, so audit conclusions depend on query access, measurement reliability, and how closely tests reflect deployment.

Latest papers

CardsList

102 papers7 papers in the last four weeks, down 53% on the four weeks before. 0.1% of all new papers.

  1. Protocol-Aware Auditing of Domain-Blind Feature Attribution in Network Intrusion Detection

    Nov 11, 2026Emmanuelli El-Mahmoud, Abanisenioluwa Kolawole Orojo, Pablo Rivas +1Feature AttributionExplainable Intrusion Detection

  2. Constructing and Validating Memorisation Audits for EHR Foundation Models

    Nov 11, 2026Inigo Stibbe, Joshua Placidi, Padmanabhan Ramnarayan +1Memorization in Language ModelsPrivacy Leakage in Language Models

  3. HydroTuring: A physics probe benchmark testing mass, energy, and momentum conservation in hydrologic models

    Nov 8, 2026Zhi Li, Changming Li, Siavash Shams +17HydrologyForecasting Benchmarks

  4. Where Is a Prediction Model Miscalibrated, and for Whom? Local Audits in Outcome-Learned Pockets

    Nov 2, 2026Bernardo Modenesi, Taoyi Chen, Sima Najafzadehkhoei +3Model CalibrationBlack-Box Model Auditing

  5. Testing concept-level audits of melanoma classifiers with diffusion counterfactuals and matched positive controls

    Nov 1, 2026Md Shohanoor Rahman, Md Hasibul Islam, Md Kishor Morol +2Explainable Medical Image AnalysisExplanation Evaluation

  6. Auditor-Assisted Summary-Channel Verification for Hosted LLM Identity Substitution

    Oct 19, 2026Ziyi Zhang, Ziyao Wang, Guoheng Sun +2LLM AuditingLLM Watermarking

  7. Blackbox Performance Analysis of LLM-based Network Control

    Oct 17, 2026Mahdi Alizadeh, Pooria Namyar, Arvin Ghavidel +1Black-Box Model AuditingLanguage Model-Based Control

  8. Dataset Inference for Data Provenance and Privacy Auditing in Tabular Foundation Models

    Oct 16, 2026Dariush Wahdany, Jesse Cresswell, Naiqing Guan +3Training Data AttributionTabular Foundation Models

  9. PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

    Oct 15, 2026Kshitij Mishra, Abhijith Sharma, Nils Lukas +1AI Agent AuditingLLM Agent Evaluation

  10. What Does an Observability Foundation Model Know?

    Oct 4, 2026Dhyey Dharmendrakumar Mavani, Rian Atri, Tairan JiTime Series ForecastingRepresentation Probing

  11. Confidence-Controlled XAI Auditing for Pedestrian Detection under Domain Shift

    Oct 1, 2026Ruben Dario Florez-ZelaExplainability EvaluationBlack-Box Model Auditing

  12. Efficient Active Auditing of Multi-Group Fairness with Bias Probes

    Sep 30, 2026Ayoub Ajarra, Debabrota BasuAlgorithmic FairnessGroup Fairness

  13. VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers

    Sep 29, 2026Miaobo Hu, Shuhao Hu, Xiaobo Guo +4Algorithmic AuditingBlack-Box Model Auditing

  14. PhysioTRACE: Provenance-Aware Stress Tests for Physiological Foundation Models

    Sep 28, 2026Ayana Mussabayeva, Anuar Aimoldin, Olivier Oullier +2Data ProvenanceElectrocardiogram Foundation Models

  15. Auditing Agent Actions through Query-Conditioned Attribution

    Sep 27, 2026Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo +1Gradient-Based AttributionAI Agent Benchmarks

  16. Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation

    Sep 26, 2026Derui Wang, Zewei Shi, Rayne Holland +4AI Agent ReliabilityBlack-Box Model Auditing

  17. Auditing System-1 Models on Biosecurity-Relevant Benchmarks: Calibration, Selective Prediction, and Permutation Instability in a Non-Generative Model

    Sep 24, 2026Kimon Antonios Provatas, Ilias Georgakopoulos-SoaresLanguage Model CalibrationSelective Prediction

  18. When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers

    Sep 24, 2026Qingyu Wu, Yuan Wei, Renju Liu +1Human Activity RecognitionAdversarial Attacks

  19. Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies

    Sep 17, 2026Hang Xiao, Chuhong Xu, Kainan Zhou +2Formal Hardware VerificationLLM Auditing

  20. Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits

    Sep 14, 2026Mohammed Ahnouch, Lotfi ElaachakAlgorithmic AuditingBlack-Box Model Auditing

  21. Operational Range Bounding in Spectroscopy: A Safety Cage Framework for Machine Learning Models

    Sep 11, 2026Nikki Grens, Luís F. Simões, Kai Hou Yip +1Scientific MLSelective Prediction

  22. Membership Inference via Pairwise Likelihood Ratios

    Sep 11, 2026Shengjie Niu, Zebin Yun, Yeheng Ge +1Membership Inference AttacksLikelihood Ratio Testing

  23. A Low Grounding Score Is Not an Ungrounded Judge: Identifying the Perceptibility Confound in Multimodal Oversight

    Sep 9, 2026Rasul Khanbayov, Hasan KurbanMultimodal Model EvaluationVLM Evaluation

  24. The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits

    Sep 8, 2026Siddharth Vohra, Manikandan RavikiranLanguage Model Bias EvaluationDemographic Bias in Language Models

  25. Black-Box Membership Inference via Word-Level Probability Estimation

    Sep 8, 2026Shengjie Niu, Yeheng Ge, Jian HuangMembership Inference AttacksPrivacy Leakage in Language Models

  26. Evaluating and Recalibrating Probabilistic Classifiers from One-Bit Threshold Queries

    Sep 4, 2026Roman Plaud, Antoine Saillenfest, Matthieu Labeau +2Language Model CalibrationUncertainty Calibration