Linear Model Extraction via Factual and Counterfactual Queries

• URL: http://arxiv.org/abs/2602.09748v1
• Date: Tue, 10 Feb 2026 12:57:53 GMT
• Title: Linear Model Extraction via Factual and Counterfactual Queries
• Abstract summary: In model extraction attacks, the goal is to reveal the parameters of a black-box machine learning model.<n>We consider linear models and three types of queries: factual, counterfactual, and robust counterfactual.
• Score: 2.6499018693213316
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In model extraction attacks, the goal is to reveal the parameters of a black-box machine learning model by querying the model for a selected set of data points. Due to an increasing demand for explanations, this may involve counterfactual queries besides the typically considered factual queries. In this work, we consider linear models and three types of queries: factual, counterfactual, and robust counterfactual. First, for an arbitrary set of queries, we derive novel mathematical formulations for the classification regions for which the decision of the unknown model is known, without recovering any of the model parameters. Second, we derive bounds on the number of queries needed to extract the model's parameters for (robust) counterfactual queries under arbitrary norm-based distances. We show that the full model can be recovered using just a single counterfactual query when differentiable distance measures are employed. In contrast, when using polyhedral distances for instance, the number of required queries grows linearly with the dimension of the data space. For robust counterfactuals, the latter number of queries doubles. Consequently, the applied distance function and robustness of counterfactuals have a significant impact on the model's security.

Related papers

• Query-efficient model evaluation using cached responses [0.2994962964425238]
  We introduce an approach for predicting benchmark performance that leverages cached model responses based on the Data Kernel Perspective Space (DKPS)<n>We demonstrate that DKPS-based methods achieve the same mean absolute error as baselines with a substantially decreased query budget.<n>We conclude by proposing an offline method for selecting a set of queries that maximizes the goodness-of-fit on reference models.
  arXiv  Detail & Related papers  (2026-05-08T01:24:06Z)
• TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering [80.93487993878836]
  A common class of real-world queries is implicitly predictive, requiring the inference of unobserved answers from historical patterns rather than mere retrieval.<n>These queries introduce two challenges: recognizing latent intent and reliable predictive reasoning over massive tables.<n>We introduce TopBench, a benchmark consisting of 779 samples across four sub-tasks, ranging from single-point prediction to decision making, treatment effect analysis, and complex reasoning.
  arXiv  Detail & Related papers  (2026-04-30T16:22:51Z)
• HuggingR$^{4}$: A Progressive Reasoning Framework for Discovering Optimal Model Companions [50.61510609116118]
  HuggingR$4$ is a novel framework that combines Reasoning, Retrieval, Refinement, and Reflection to efficiently select models.<n>It attains a workability rate of 92.03% and a reasonability rate of 82.46%, surpassing existing method by 26.51% and 33.25% respectively.
  arXiv  Detail & Related papers  (2025-11-24T03:13:45Z)
• From Black-box to Causal-box: Towards Building More Interpretable Models [57.23201263629627]
  We introduce the notion of causal interpretability, which formalizes when counterfactual queries can be evaluated from a specific class of models.<n>We derive a complete graphical criterion that determines whether a given model architecture supports a given counterfactual query.
  arXiv  Detail & Related papers  (2025-10-24T20:03:18Z)
• Model Correlation Detection via Random Selection Probing [62.093777777813756]
  Existing similarity-based methods require access to model parameters or produce scores without thresholds.<n>We introduce Random Selection Probing (RSP), a hypothesis-testing framework that formulates model correlation detection as a statistical test.<n>RSP produces rigorous p-values that quantify evidence of correlation.
  arXiv  Detail & Related papers  (2025-09-29T01:40:26Z)
• Reasoning Models are Test Exploiters: Rethinking Multiple-Choice [12.317748510370238]
  Large Language Models (LLMs) are asked to choose among a fixed set of choices.<n>Multiple-choice question-answering (McQCA) is a good proxy for the downstream performance of models.<n>This paper investigates the extent to which this trend continues to hold for state-of-the-art reasoning models.
  arXiv  Detail & Related papers  (2025-07-21T07:49:32Z)
• Exploring Query Efficient Data Generation towards Data-free Model Stealing in Hard Label Setting [38.755154033324374]
  Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training data.<n>This paper presents a new data-free model stealing approach called Query Efficient Data Generation (textbfQEDG)<n>We introduce two distinct loss functions to ensure the generation of sufficient samples that closely and uniformly align with the target model's decision boundary.
  arXiv  Detail & Related papers  (2024-12-18T03:03:15Z)
• FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning [12.894941192080616]
  FormulaReasoning is a new dataset specifically designed for formula-based numerical reasoning.<n>It consists of 5,324 questions that require numerical calculations grounded in external physics formulas.<n>We analyze various reasoning approaches on FormulaReasoning, with emphasis on comparative evaluation of different architectural and methodological frameworks.
  arXiv  Detail & Related papers  (2024-02-20T03:39:49Z)
• Predictive Querying for Autoregressive Neural Sequence Models [23.85426261235507]
  We introduce a general typology for predictive queries in neural autoregressive sequence models. We show that such queries can be systematically represented by sets of elementary building blocks. We leverage this typology to develop new query estimation methods.
  arXiv  Detail & Related papers  (2022-10-12T17:59:36Z)
• You Only Need One Model for Open-domain Question Answering [26.582284346491686]
  Recent works for Open-domain Question Answering refer to an external knowledge base using a retriever model. We propose casting the retriever and the reranker as hard-attention mechanisms applied sequentially within the transformer architecture. We evaluate our model on Natural Questions and TriviaQA open datasets and our model outperforms the previous state-of-the-art model by 1.0 and 0.7 exact match scores.
  arXiv  Detail & Related papers  (2021-12-14T13:21:11Z)
• Model-agnostic multi-objective approach for the evolutionary discovery of mathematical models [55.41644538483948]
  In modern data science, it is more interesting to understand the properties of the model, which parts could be replaced to obtain better results. We use multi-objective evolutionary optimization for composite data-driven model learning to obtain the algorithm's desired properties.
  arXiv  Detail & Related papers  (2021-07-07T11:17:09Z)
• An exact counterfactual-example-based approach to tree-ensemble models interpretability [0.0]
  High-performance models do not exhibit the necessary transparency to make their decisions fully understandable. We could derive an exact geometrical characterisation of their decision regions under the form of a collection of multidimensional intervals. An adaptation to reasoning on regression problems is also envisaged.
  arXiv  Detail & Related papers  (2021-05-31T09:32:46Z)
• When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model [87.25037167380522]
  We propose a model that is accurate, robust, efficient, generalizable, and end-to-end trainable. In order to achieve a better accuracy, we propose two lightweight modules. DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one.
  arXiv  Detail & Related papers  (2021-05-27T13:51:42Z)
• When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data [84.87772675171412]
  We study the circumstances under which explanations of individual data points can improve modeling performance. We make use of three existing datasets with explanations: e-SNLI, TACRED, SemEval.
  arXiv  Detail & Related papers  (2021-02-03T18:57:08Z)

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.