{"slug": "cafd-concept-aware-dnn-fault-detection-using-vlms", "title": "CAFD: Concept-Aware DNN Fault Detection using VLMs", "summary": "Researchers have developed Concept-Aware Fault Detection (CAFD), a learning-based method that improves fault detection in deep neural networks by integrating model-based, distance-based, and a novel concept-based feature called Concept Failure Ratio (CFR). CFR uses Vision-Language Models to extract textual concepts from images and quantify their association with DNN failures, providing complementary semantic information. In tests across three DNN models and datasets including ImageNet, CAFD outperformed five state-of-the-art baselines, achieving an average 18.3% improvement in Fault Detection Rate across constrained selection budgets.", "body_md": "arXiv:2605.24008v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/cafd-concept-aware-dnn-fault-detection-using-vlms", "canonical_source": "https://arxiv.org/abs/2605.24008", "published_at": "2026-05-26 04:00:00+00:00", "updated_at": "2026-05-26 04:06:46.364854+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "neural-networks", "computer-vision", "ai-safety"], "entities": ["CAFD", "DNN", "VLM", "ImageNet"], "alternates": {"html": "https://wpnews.pro/news/cafd-concept-aware-dnn-fault-detection-using-vlms", "markdown": "https://wpnews.pro/news/cafd-concept-aware-dnn-fault-detection-using-vlms.md", "text": "https://wpnews.pro/news/cafd-concept-aware-dnn-fault-detection-using-vlms.txt", "jsonld": "https://wpnews.pro/news/cafd-concept-aware-dnn-fault-detection-using-vlms.jsonld"}}