# CAFD: Concept-Aware DNN Fault Detection using VLMs

arXiv: https://arxiv.org/abs/2605.24008 · HTML: https://mlsanity.com/paper/2605.24008/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems](https://mlsanity.com/paper/1803.07519/) (2018)
- [Guiding Deep Learning System Testing using Surprise Adequacy](https://mlsanity.com/paper/1808.08444/) (2018)
- [Text-To-Concept (and Back) via Cross-Model Alignment](https://mlsanity.com/paper/2305.06386/) (2023)
- [A Survey on Deep Learning for Software Engineering](https://mlsanity.com/paper/2011.14597/) (2020)
- [Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning (Replicability Study)](https://mlsanity.com/paper/2205.00664/) (2022)
- [Boosting Operational DNN Testing Efficiency through Conditioning](https://mlsanity.com/paper/1906.02533/) (2019)
- [Black-Box Testing of Deep Neural Networks Through Test Case Diversity](https://mlsanity.com/paper/2112.12591/) (2021)
- [Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning](https://mlsanity.com/paper/2002.00863/) (2020)
- [DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks](https://mlsanity.com/paper/2303.04878/) (2023)
- [TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks](https://mlsanity.com/paper/2105.10113/) (2021)
- [Concept-based Analysis of Neural Networks via Vision-Language Models](https://mlsanity.com/paper/2403.19837/) (2024)
- [Evaluating the Robustness of Test Selection Methods for Deep Neural Networks](https://mlsanity.com/paper/2308.01314/) (2023)
- [Calibrated neighborhood aware confidence measure for deep metric learning](https://mlsanity.com/paper/2006.04935/) (2020)
- [TEASMA: A Practical Methodology for Test Adequacy Assessment of Deep Neural Networks](https://mlsanity.com/paper/2308.01311/) (2023)
- [Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)](https://mlsanity.com/paper/2503.17416/) (2025)
- [MetaSel: A Test Selection Approach for Fine-tuned DNN Models](https://mlsanity.com/paper/2503.17534/) (2025)
- [A Highly Efficient Diversity-based Input Selection for DNN Improvement Using VLMs](https://mlsanity.com/paper/2601.08024/) (2026)

## Abstract (arXiv)

Fault detection for Deep Neural Networks (DNNs) has received increasing attention in recent years. While more advanced hybrid approaches have been proposed to combine multiple sources of information and outperform earlier techniques, they often incur substantial computational overhead, limiting scalability and practicality in real-world settings. In this paper, we introduce Concept-Aware Fault Detection (CAFD), a learning-based approach that achieves superior fault detection performance by effectively integrating multiple information sources while maintaining practical efficiency. Specifically, CAFD is trained using a carefully selected set of informative features, including model-based signals derived from the DNN's outputs, distance-based features, and a novel concept-based feature, called Concept Failure Ratio (CFR). CFR leverages Vision-Language Models (VLMs) to extract textual concepts from images and quantify the likelihood that their presence is associated with DNN failures. By incorporating this feature, CAFD benefits from complementary semantic information, enabling more effective fault detection. Our results demonstrate that CFR serves as an effective indicator for DNN fault detection. We conduct an extensive empirical evaluation of CAFD, comparing it against five state-of-the-art baselines across three subject DNN models and datasets, including ImageNet. Across a wide range of constrained selection budgets, CAFD consistently outperforms all baselines in Fault Detection Rate (FDR), achieving average FDR improvements of 18.3% across all investigated subjects and budget sizes.