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

Agent Step Value: Auditing Evaluator-Channel Reversals in Black-Box Agent Traces
Jul 5, 2026Andrew Zhang, Chengzhan LiLLM Agent Evaluation AI Agent Evaluation
KTH Royal Institute of Technology · University of Electronic Science and Technology of China
Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations
Jul 1, 2026Alexander Chemeris, Ming Jin, Randall BalestrieroSynthetic Benchmark Generation Time Series Representation Learning
Langotime South Africa · Griffith University Australia · Brown University United States
Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale
Jun 29, 2026Alessandro Morosini, Sarah H. Cen, Andrew Ilyas +3Algorithmic Auditing Algorithmic Bias
Massachusetts Institute of Technology · Carnegie Mellon University
Sequential Fairness Auditing with Limited Output Access
Jun 29, 2026Ioannis Pitsiorlas, Martha V. Sourla, Marios KountourisAlgorithmic Fairness Group Fairness
EURECOM, France · DaSCI, University of Granada, Spain
RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
Jun 26, 2026Xuan Zhao, Lena Krieger, Zhuo Cao +3Surrogate Modeling Model Extraction Attacks
IAS-8, Forschungszentrum Jülich, Germany · LMU Munich, Munich Center for Machine Learning (MCML), Germany · Department of Computer Science, Aarhus University, Denmark
Where Black-box Drug-Target Interaction Prediction Models Look: Cross-Method Explainability
Jun 12, 2026Ali Vefghi, Zahed Rahmati, Mohammad AkbariFeature Attribution Explainability Evaluation
Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran
A prior-free blind detection of information leakage from model predictions
Jun 9, 2026Laurence A. JacobsData Leakage Black-Box Model Auditing
Center for Molecular Cardiology, University of Zurich, Zurich, Switzerland · Center for Complexity Sciences, National University of Mexico, Mexico City, Mexico
Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models
Jun 8, 2026Jianwei TaiData Leakage Adversarial Attacks
School of Internet, Anhui University
Evaluating AI Investment Strategies
Jun 7, 2026Irene AldridgeAlgorithmic Auditing Policy Evaluation
Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard
Jun 7, 2026Alireza Arbabi, Florian KerschbaumLLM Alignment LLM Auditing
Department of Computer Science, University of Waterloo, Waterloo, ON, Canada · Vector Institute, Toronto, ON, Canada
MC-PDD: Masked Corpus-Level Pretraining Data Detection for Black-Box Large Language Models
Jun 6, 2026Kaixin Lan, Mu You, Tao Fang +3Membership Inference Attacks LLM Auditing
Natural Language Processing & Portuguese-Chinese Machine Translation (NLP2CT) Laboratory, University of Macau, Macau SAR, China · Institute of International Language Services Studies, Macau Millennium College, Macau SAR, China · Innovation Research & Development, BoardWare Information System Limited
Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2
Jun 5, 2026Daniel DeAlcala, Gonzalo Mancera, Julian Fierrez +3Membership Inference Attacks Privacy Leakage in Language Models
BiometricsAI, Universidad Aut´onoma de Madrid, Spain
Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity
May 29, 2026Ibne Farabi Shihab, Sanjeda Akter, Anuj SharmaInformation-Theoretic Lower Bounds Black-Box Model Auditing
Department of Computer Science, Iowa State University · Department of Civil, Construction & Environmental Engineering, Iowa State University
Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
May 28, 2026Shahinul Hoque, Jinghuai Zhang, Jinyuan Sun +1LLM Auditing Black-Box Model Auditing
University of Tennessee, Knoxville · University of California, Los Angeles
Auditing Training Data in Generative Music Models via Black-Box Membership Inference
May 28, 2026Yi Chen Liu, Jiawei Yu, Kexin Cao +3Text-to-Music Generation Membership Inference Attacks
University of Georgia, Athens, GA, USA · Independent Researcher · University of Tennessee, Knoxville, TN, USA
Symmetry Defeats Auditing
May 27, 2026Nick Merrill, Zeke MedleyAlgorithmic Auditing Adversarial Attacks
UC Berkeley · Forecasting Research Institute · Northeastern University
Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice
May 26, 2026Yingshuo Wang, Xian Sun, Yanhang Li +2Tabular Foundation Models Discrete Choice Modeling
University of California, Berkeley, CA, USA · Duke University, Durham, NC, USA · Northeastern University, Boston, MA, USA +2
Unlocking Apple's Private Cloud Compute: An Analysis of Privacy-Preserving Artificial Intelligence
May 22, 2026Yannik Dittmar, Marvin Jerome Stephan, Thomas Völkl +2Privacy Auditing Privacy-Preserving Language Models
Hasso Plattner Institute, University of Potsdam Potsdam, Germany · TU Darmstadt, Secure Mobile Networking Lab Darmstadt, Germany · TU Darmstadt, Secure Mobile Networking Lab, Darmstadt, Germany +1
Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning
May 21, 2026Benjamin D. Kim, Lav R. Varshney, Daniel AlabiPrivacy Auditing Black-Box Model Auditing
University of Illinois Urbana-Champaign · 1Massachusetts Institute of Technology · Brook University
I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models
May 20, 2026Barbara Tarantino, Gennaro Auricchio, Paolo GiudiciAlgorithmic Auditing Black-Box Model Auditing
Department of Economics, University of Pavia, Via S. Felice Al Monastero, 5, Pavia, 27100, Italy · Department of Mathematics, University of Padua, Via Trieste, 63, Padua, 35131, Italy
How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence
May 19, 2026Yue Chen, Yihao Wang, Ziyi Tang +2Document Parsing Document Layout Analysis
Sun Yat-sen University · Chaotic Pendulum Lab · Nanyang Technological University
Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands
May 14, 2026Pratinav Seth, Vinay Kumar SankarapuAI Assurance AI Governance
Lexsi Labs
Architecture-Aware Explanation Auditing for Industrial Visual Inspection
May 14, 2026Sibo Jia, Zihang Zhao, Kunrong LiIndustrial Inspection Explainability Evaluation
Dublin College, Beijing University of Technology, Beijing, P.R. China · College of Computer Science, Beijing University of Technology, P.R. China
Black-box model classification under the discriminative factorization
May 8, 2026Hayden Helm, Merrick Ohata, Carey PriebeClassification Black-Box Model Auditing
Helivan · JHU
Beyond the Wrapper: Identifying Artifact Reliance in Static Malware Classifiers using TRUSTEE
May 7, 2026Riyazuddin Mohammed, Lan ZhangMalware Classification Malware Analysis
School of Informatics, Computing, and Cyber Systems
Narrow Secret Loyalty Dodges Black-Box Audits
May 7, 2026Alfie Lamerton, Fabien RogerData Poisoning Attacks Black-Box Model Auditing
Formation Research
ISAAC: Auditing Causal Reasoning in Deep Models for Drug-Target Interaction
May 3, 2026Barbara Tarantino, Sun Kim, Yijingxiu Lu +1Reasoning Evaluation Causal Interpretability
Department of Economics and Management, University of Pavia, Pavia, Italy · Department of Computer Science and Engineering, Seoul National University, Gwanak-gu 08826, Korea.
Bounding the Black Box: A Statistical Certification Framework for AI Risk Regulation
Apr 23, 2026Natan Levy, Gadi PerlAI Assurance AI Risk Management
School of Computer Science and Engineering The Hebrew University of Jerusalem(HUJI) Jerusalem, Israel · dept. name of organization (of Aff.) The Hebrew University of Jerusalem(HUJI) Jerusalem, Israel
Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways
Apr 22, 2026Guanjie Lin, Yinxin Wan, Shichao Pei +3LLM Auditing Black-Box Model Auditing
University of Massachusetts Boston · Boston, Massachusetts, USA · Arizona State University +2
Identifying Ethical Biases in Action Recognition Models
Apr 20, 2026Ana Baltaretu, Pascal Benschop, Jan van GemertHuman Activity Recognition Algorithmic Fairness
1EEMCS, Delft University of Technology, The Netherlands

Jul 5, 2026, cs.AIJ/K move · Enter open · S save

Agent Step Value: Auditing Evaluator-Channel Reversals in Black-Box Agent Traces

Andrew Zhang, Chengzhan Li

KTH Royal Institute of Technology · University of Electronic Science and Technology of China

LLM Agent Evaluation AI Agent Evaluation Agent Evaluation Black-Box Model Auditing

Open paper AskPDF arXiv

When evaluator-derived step rewards are pooled or compared across scoring channels, their sign is treated as transportable. Yet the same frozen transition can change sign with the scoring channel. Process rewards vary agent states, while evaluator audits vary scoring configurations; neither first difference isolates their interaction. We define Agent Step Value (ASV) as channel-indexed target-margin gain and identify the missing state-by-channel interaction by replaying complete faces. Of 1,100 PubMed open question-answering transitions, 1,004 were complete across four cyclic layouts. Their mean update is positive under direct scoring (+0.163 [0.102, 0.218]) and negative with an externally generated view (-0.160 [-0.244, -0.079]), giving an interaction of -0.323 [-0.418, -0.232]. Across paired transitions, 507/1,004 cross zero in one direction or the other. Matched templates isolate a generated-minus-quote interaction of -1.121 [-1.534, -0.703]. Its direction remains negative after the readout and evaluator-stack changes, and quote yields a higher paired area under the receiver operating characteristic curve (AUC) for stored success at all three bridge vertices. Because the two views preserve the same task information conditional on the retained state, a representation-invariance null predicts equal responses and success rankings across them. ASV provides a transport audit for evaluator-derived step measurements; causal actor credit lies outside its estimand.

Momentum

Related topics

Latest papers 66