UNBOX: Unveiling Black-box visual models with Natural-language

• URL: http://arxiv.org/abs/2603.08639v1
• Date: Mon, 09 Mar 2026 17:16:39 GMT
• Title: UNBOX: Unveiling Black-box visual models with Natural-language
• Abstract summary: We introduce UNBOX, a framework for class-wise model dissection under fully data-free, gradient-free, and backpropagation-free constraints.<n>We evaluate UNBOX on ImageNet-1K, Waterbirds, and CelebA through semantic fidelity tests, visual-feature correlation analyses, and slice-discovery auditing.
• Score: 50.433977345786055
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only output probabilities and hiding architecture, parameters, gradients, and training data. This opacity prevents meaningful auditing, bias detection, and failure analysis. Existing explanation methods assume white- or gray-box access or knowledge of the training distribution, making them unusable in these real-world settings. We introduce UNBOX, a framework for class-wise model dissection under fully data-free, gradient-free, and backpropagation-free constraints. UNBOX leverages Large Language Models and text-to-image diffusion models to recast activation maximization as a purely semantic search driven by output probabilities. The method produces human-interpretable text descriptors that maximally activate each class, revealing the concepts a model has implicitly learned, the training distribution it reflects, and potential sources of bias. We evaluate UNBOX on ImageNet-1K, Waterbirds, and CelebA through semantic fidelity tests, visual-feature correlation analyses and slice-discovery auditing. Despite operating under the strictest black-box constraints, UNBOX performs competitively with state-of-the-art white-box interpretability methods. This demonstrates that meaningful insight into a model's internal reasoning can be recovered without any internal access, enabling more trustworthy and accountable visual recognition systems.

Related papers

• S$^2$COPE: Self-Supervised Concept Discovery via Preference Learning [15.951097715837799]
  We introduce Self-Supervised Concept discOvery via Preference lEarning (model), a label-free framework that resolves this dilemma.<n>Our work suggest that interpretability can emerge through a model's autonomous interaction with incidental visual structures, without any human supervision.
  arXiv  Detail & Related papers  (2026-06-12T16:02:44Z)
• Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? [53.07826484214082]
  We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis.<n>Pando predicts held-out model decisions from $10$ labeled query-response pairs.<n>When explanations are faithful, black-box elicitation matches or exceeds all white-box methods.
  arXiv  Detail & Related papers  (2026-04-13T06:42:24Z)
• Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content [53.93606081932928]
  We introduce a novel black box detection framework that requires only API access.<n>We measure the likelihood that the image was generated by the model itself.<n>For black-box models that do not support masked image inputs, we incorporate a cost efficient surrogate model trained to align with the target model distribution.
  arXiv  Detail & Related papers  (2025-05-02T05:11:35Z)
• Investigating the Duality of Interpretability and Explainability in Machine Learning [2.8311451575532156]
  Complex "black box" models exhibit exceptional predictive performance.<n>Their inherently opaque nature raises concerns about transparency and interpretability.<n>Efforts are focused on explaining these models instead of developing ones that are inherently interpretable.
  arXiv  Detail & Related papers  (2025-03-27T10:48:40Z)
• Predicting the Performance of Black-box LLMs through Self-Queries [60.87193950962585]
  Large language models (LLMs) are increasingly relied on in AI systems, predicting when they make mistakes is crucial.<n>In this paper, we extract features of LLMs in a black-box manner by using follow-up prompts and taking the probabilities of different responses as representations.<n>We demonstrate that training a linear model on these low-dimensional representations produces reliable predictors of model performance at the instance level.
  arXiv  Detail & Related papers  (2025-01-02T22:26:54Z)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable? [8.391254800873599]
  We introduce a method to perform concept-based interventions on pretrained neural networks, which are not interpretable by design. We formalise the notion of intervenability as a measure of the effectiveness of concept-based interventions and leverage this definition to fine-tune black boxes.
  arXiv  Detail & Related papers  (2024-01-24T16:02:14Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Recurrence-Aware Long-Term Cognitive Network for Explainable Pattern Classification [0.0]
  We propose an LTCN-based model for interpretable pattern classification of structured data. Our method brings its own mechanism for providing explanations by quantifying the relevance of each feature in the decision process. Our interpretable model obtains competitive performance when compared to the state-of-the-art white and black boxes.
  arXiv  Detail & Related papers  (2021-07-07T18:14:50Z)
• Learning Global Transparent Models Consistent with Local Contrastive Explanations [34.86847988157447]
  We create custom features from sparse local contrastive explanations of the black-box model and then train a globally transparent model on just these. Based on a key insight we propose a novel method where we create custom features from sparse local contrastive explanations of the black-box model and then train a globally transparent model on just these.
  arXiv  Detail & Related papers  (2020-02-19T15:45:42Z)

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.