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.

翻译：确保开放世界视觉识别的可信性需要模型具备可解释性、公平性以及对分布偏移的鲁棒性。然而，现代视觉系统越来越多地作为专有黑盒API部署，仅公开输出概率，而隐藏架构、参数、梯度和训练数据。这种不透明性阻碍了有效的审计、偏差检测和故障分析。现有的解释方法假设具备白盒或灰盒访问权限或了解训练分布，使其无法适用于这些现实场景。我们提出了UNBOX框架，用于在完全无数据、无梯度且无需反向传播的约束下进行逐类别模型剖析。UNBOX利用大型语言模型和文生图扩散模型，将激活最大化重新定义为纯粹由输出概率驱动的语义搜索。该方法生成可人类解读的文本描述符，以最大化激活每个类别，从而揭示模型隐式学习的概念、其反映的训练分布以及潜在的偏差来源。我们通过语义保真度测试、视觉特征相关性分析和切片发现审计，在ImageNet-1K、Waterbirds和CelebA数据集上评估UNBOX。尽管在最为严格的黑盒约束下运行，UNBOX的性能仍与最先进的白盒可解释性方法具有竞争力。这表明，无需任何内部访问即可恢复对模型内部推理机制的有意义洞察，从而构建更可信、更负责任的视觉识别系统。