Black-Box Model Auditing

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

PairAudit: Guiding Human Review with Graph Tokens under Distribution Shift
Oct 7, 2026Jiran Tao, Binyan JiangNetwork Intrusion Detection Black-Box Model Auditing
The Hong Kong Polytechnic University
What Does an Observability Foundation Model Know?
Oct 4, 2026Dhyey Dharmendrakumar Mavani, Rian Atri, Tairan JiTime Series Forecasting Representation Probing
Independent · Keiji AI
Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model
Oct 1, 2026Sharath M Shankaranarayana, Davor Runje, Jan JanninkProbability Calibration Black-Box Model Auditing
Efficient Active Auditing of Multi-Group Fairness with Bias Probes
Sep 30, 2026Ayoub Ajarra, Debabrota BasuAlgorithmic Fairness Group Fairness
´Equipe Scool, Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189- CRIStAL
VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers
Sep 29, 2026Miaobo Hu, Shuhao Hu, Xiaobo Guo +5Algorithmic Auditing Black-Box Model Auditing
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
PhysioTRACE: Provenance-Aware Stress Tests for Physiological Foundation Models
Sep 28, 2026Ayana Mussabayeva, Anuar Aimoldin, Olivier Oullier +2Data Provenance Electrocardiogram Foundation Models
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE · McGill University, Montreal, Canada · Carnegie Mellon University, Pittsburgh, USA
Auditing Agent Actions through Query-Conditioned Attribution
Sep 27, 2026Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo +1Gradient-Based Attribution AI Agent Benchmarks
University of Illinois Urbana-Champaign · IBM
When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers
Sep 24, 2026Qingyu Wu, Yuan Wei, Renju Liu +1Human Activity Recognition Adversarial Attacks
Defense Innovation Institute, Academy of Military Science, Beijing, China · School of Software Engineering, South China University of Technology, Guangzhou, China
The Delegation Blind Spot: Auditing Product Decisions from Agent Choices
Sep 22, 2026Shivam GuptaAI Agent Auditing Partial Identification
Independent Research
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 Verification LLM Auditing
Fortinet, Inc. Sunnyvale, CA, USA · Sony Corporate of America San Jose, CA, USA · Google LLC Mountain View, CA, USA
Membership Inference via Pairwise Likelihood Ratios
Sep 14, 2026Shengjie Niu, Zebin Yun, Yeheng Ge +1Membership Inference Attacks Black-Box Model Auditing
The Hong Kong Polytechnic University, Hong Kong, China · Tel Aviv University, Israel
Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits
Sep 14, 2026Mohammed Ahnouch, Lotfi ElaachakAlgorithmic Auditing Black-Box Model Auditing
Université Paris 1 Paris, France · Faculty of Science and Technology of Tangier Abdelmalek Essaadi University Tangier, Morocco
The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits
Sep 8, 2026Siddharth Vohra, Manikandan RavikiranLanguage Model Bias Evaluation Demographic Bias in Language Models
Carnegie Mellon University Amazon Web Services AI Native Pittsburgh, PA, USA · Indian Institute of Technology Mandi, India
Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints
Sep 3, 2026Haoyaun Zhu, Jie ZhangLLM Evaluation LLM-as-a-Judge
School of Electronic and Electrical Engineering, University of Sheffield, Sheffield S10 2TN, UK · R&D Department, Ranplan Wireless Network Design Ltd., Cambridge CB23 3UY, UK · R&D Department, Cambridge AI+ Ltd., Cambridge CB23 3UY, UK
Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG
Sep 3, 2026Alexandr Goultiaev Tolstokorov, Kyriakos Mouratidis, Javad Dogani +1Dataset Watermarking RAG Security
IMDEA Networks Institute, Madrid, Spain · Universidad Carlos III de Madrid, Madrid, Spain · Singapore Management University, Singapore
Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification
Aug 31, 2026Yisen XiLanguage Model Fingerprinting Black-Box Model Auditing
Independent Researcher, Beijing, China
BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
Aug 31, 2026Adrians Skapars, Edoardo ManinoLanguage Model Steering Language Model Safety Evaluation
University of Manchester, United Kingdom
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification
Aug 28, 2026Cameron Wilding, Mina Shaker, Fatemeh GanjiLLM Auditing Privacy-Preserving ML
Worcester Polytechnic Institute Worcester, MA, USA
When Explanations Betray Backdoors: Black-Box Auditing for Language Model Classifiers
Aug 12, 2026Yang Liu, Ran ZouLLM Backdoor Attacks Backdoor Detection
Department of Statistics and Operations Research, University of North Carolina at Chapel Hill · Department of Statistics, University of California, Irvine
Relational Response Fields: A General Theory of Black-Box LLM Response Consistency and Recovery
Aug 5, 2026Song ZichenLLM Reliability Corruption Robustness
Sungkyunkwan University
Manipulation-Proof Oblivious Audits against Deceptive Model Providers
Aug 5, 2026Augustin Godinot, Sofiane Azogagh, Julien Ferry +1Algorithmic Fairness Black-Box Model Auditing
1INRIA Centre de l’Universit´e de Rennes, France · 2EURECOM, Sophia Antipolis, France · 3CIRRELT & SCALE-AI Chair in Data-Driven Supply Chains, Department of Mathematics and Industrial Engineering, Polytechnique Montr´eal, Canada +1
Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
Aug 3, 2026Zirui Huang, Yunlong Mao, Wei Tong +3Language Model Fingerprinting Training Data Attribution
State Key Laboratory of Novel Software Technology, Nanjing University Nanjing, Jiangsu, China
Latent-Regime Bias Auditing for Volatility Forecasting
Aug 3, 2026Arthur Chagas, Pedro Bento, Yan Aquino +3Time Series Forecasting Financial Time Series
Department of Computer Science Universidade Federal de Minas Gerais – UFMG Belo Horizonte, Brazil
When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design
Aug 2, 2026Shuangxiu, Ma, Wenhe +1Surrogate Modeling Surrogate-Assisted Optimization
Max · William G. Lowrie Department of Chemical and Biomolecular Engineering, The Ohio State University, Columbus, Ohio 43210, United States · Zachary +1
Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong
Jul 26, 2026Suramya R. Angdembay, Dikshant Aryal, Nick RahimiCoT Faithfulness CoT Evaluation
The University of Southern Mississippi
Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification
Jul 23, 2026Carter Luck, Olive Franzese-McLaughlin, Elisaweta Masserova +3Privacy-Preserving ML Black-Box Model Auditing
University of Massachusetts Amherst · Vector Institute · University of Toronto +3
HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks
Jul 21, 2026Haozhe JiaLLM Auditing Temporal Data Leakage
University College Dublin
Bet on Features: Anytime-Valid and Feature-Aware Auditing of Conditional Quantile Forecasters
Jul 13, 2026Ivane Antonov, Sohom Mukherjee, Richard Pibernik +1Quantile Regression Sequential Hypothesis Testing
Julius-Maximilians-Universität Würzburg · INSEAD
Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
Jul 9, 2026Jack Hopkins, Dipika Khullar, Fabien RogerOverthinking in Language Models Privacy Leakage in Language Models
Anthropic Fellows Program · MATS · Anthropic.
SHARC: SHAP-Based Interpretability in Machine Learning Risk Models for Regulatory Capital under ICAAP and CCAR
Jul 6, 2026Ujjwala VadrevuAI Risk Management Black-Box Model Auditing

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

PairAudit: Guiding Human Review with Graph Tokens under Distribution Shift

Jiran Tao, Binyan Jiang

The Hong Kong Polytechnic University

Network Intrusion Detection Black-Box Model Auditing Anomaly Detection OOD Detection

Open paper AskPDF arXiv

Intrusion detectors can confidently misclassify attacks that were not seen during training. Human review can correct these errors, but only a limited number of cases can be checked. Uncertainty-based review may overlook confident errors, while anomaly scores alone do not show whether changing the review plan will correct more errors. We introduce PairAudit to find overlooked errors and improve review under a fixed budget. Its graph tokens capture prediction patterns across connected nodes. Rather than building another predictor through feature aggregation, PairAudit uses unusual relational patterns to uncover potential errors in existing predictions. Human feedback then helps decide whether these findings justify changing review priorities. Experiments across security tasks show that PairAudit corrects more errors on average than uncertainty-based review, including more errors on unseen attacks. These gains account for all review costs and do not require retraining the detector.

Momentum

Related topics

Latest papers 66