Deep learning models for Electrocardiogram (ECG) diagnosis have achieved remarkable accuracy but exhibit fragility against adversarial perturbations, particularly Smooth Adversarial Perturbations (SAP) that mimic biological morphology. Existing defenses face a critical dilemma: Adversarial Training (AT) provides robustness but incurs a prohibitive computational burden, while certified methods like Randomized Smoothing (RS) introduce significant inference latency, rendering them impractical for real-time clinical monitoring. We posit that this vulnerability stems from the models' reliance on non-robust spurious correlations rather than invariant pathological features. To address this, we propose Causal Physiological Representation Learning (CPR). Unlike standard denoising approaches that operate without semantic constraints, CPR incorporates a Physiological Structural Prior within a causal disentanglement framework. By modeling ECG generation via a Structural Causal Model (SCM), CPR enforces a structural intervention that strictly separates invariant pathological morphology (P-QRS-T complex) from non-causal artifacts. Empirical results on PTB-XL demonstrate that CPR significantly outperforms standard clinical preprocessing methods. Specifically, under SAP attacks, CPR achieves an F1 score of 0.632, surpassing Median Smoothing (0.541 F1) by 9.1%. Crucially, CPR matches the certified robustness of Randomized Smoothing while maintaining single-pass inference efficiency, offering a superior trade-off between robustness, efficiency, and clinical interpretability.

翻译：用于心电图（ECG）诊断的深度学习模型已取得显著准确率，但在对抗性扰动（尤其是模拟生物形态的平滑对抗性扰动（SAP））面前表现出脆弱性。现有防御方法面临一个关键困境：对抗训练（AT）能提供鲁棒性但带来极高的计算负担，而随机平滑（RS）等认证方法则引入显著的推理延迟，使其难以应用于实时临床监测。我们认为这种脆弱性源于模型对非鲁棒伪相关而非不变病理特征的依赖。为此，我们提出因果生理表征学习（CPR）。与在无语义约束下运行的标准去噪方法不同，CPR将生理结构先验整合到因果解耦框架中。通过结构因果模型（SCM）对ECG生成过程进行建模，CPR强制执行结构干预，严格分离不变病理形态（P-QRS-T波群）与非因果伪影。在PTB-XL数据集上的实验结果表明，CPR显著优于标准临床预处理方法。具体而言，在SAP攻击下，CPR取得0.632的F1分数，较中值平滑（0.541 F1）提升9.1%。至关重要的是，CPR在保持单次推理效率的同时，达到了与随机平滑相当的认证鲁棒性，从而在鲁棒性、效率与临床可解释性之间实现了更优的权衡。