一句话：探讨以因果推断、反事实分析和结构因果模型修复DNN失效，并梳理其在公平性、鲁棒性与后门缓解中的机遇与挑战。
深度神经网络常依赖统计相关性而非因果推理，导致鲁棒性与可解释性受限；测试虽能发现失败，但有效调试与修复仍很困难。本文探讨将因果推断作为DNN修复的主要途径，借助因果调试、反事实分析和结构因果模型来定位并纠正模型失效。作者论述这些技术如何通过有针对性的干预支持公平性、对抗鲁棒性与后门缓解，并指出该方向在可扩展性、泛化能力和计算效率方面面临的关键挑战。最后，文章展望了将因果驱动干预集成到DNN可靠性提升中的未来方向。本文属展望/立场性工作，未报告具体实验评估。
Deep Neural Networks (DNNs) often rely on statistical correlations rather than causal reasoning, limiting their robustness and interpretability. While testing methods can identify failures, effective debugging and repair remain challenging. This paper explores causal inference as an approach primarily for DNN repair, leveraging causal debugging, counterfactual analysis, and structural causal models (SCMs) to identify and correct failures. We discuss in what ways these techniques support fairness, adversarial robustness, and backdoor mitigation by providing targeted interventions. Finally, we discuss key challenges, including scalability, generalization, and computational efficiency, and outline future directions for integrating causality-driven interventions to enhance DNN reliability.