用因果推理修复深度神经网络，提升可靠性与可解释性。
Causality-Driven Neural Network Repair: Challenges and Opportunities
- 基于因果模型和反事实分析定位网络缺陷
- 可针对性提升公平性、抗攻击性和防后门能力
- 适合关注模型可信度与安全性的研究者
深度神经网络常依赖统计相关而非因果推理，限制了其鲁棒性和可解释性。尽管测试方法能发现故障，但有效调试与修复仍具挑战。本文探讨将因果推断用于深度神经网络修复，利用因果调试、反事实分析及结构因果模型（SCMs）识别并纠正错误。这些技术可通过针对性干预，提升公平性、对抗鲁棒性与后门防御能力。最后，文章讨论了可扩展性、泛化能力和计算效率等关键挑战，并展望了未来将因果驱动干预融入提升深度神经网络可靠性的方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。