Hardware trojan detection requires accurate identification and interpretable explanations for security engineers to validate and act on results. This work compares three explainability categories for gate-level trojan detection on the Trust-Hub benchmark: (1) domain-aware property-based analysis of 31 circuit-specific features from gate fanin patterns, flip-flop distances, and I/O connectivity; (2) case-based reasoning using k-nearest neighbors for precedent-based explanations; and (3) model-agnostic feature attribution (LIME, SHAP, gradient). Results show different advantages per approach. Property-based analysis provides explanations through circuit concepts like "high fanin complexity near outputs indicates potential triggers." Case-based reasoning achieves 97.4% correspondence between predictions and training exemplars, offering justifications grounded in precedent. LIME and SHAP provide feature attributions with strong inter-method correlation (r=0.94, p<0.001) but lack circuit-level context for validation. XGBoost classification achieves 46.15% precision and 52.17% recall on 11,392 test samples, a 9-fold precision improvement over prior work (Hasegawa et al.: 5.13%) while reducing false positive rates from 5.6% to 0.25%. Gradient-based attribution runs 481 times faster than SHAP but provides similar domain-opaque insights. This work demonstrates that property-based and case-based approaches offer domain alignment and precedent-based interpretability compared to generic feature rankings, with implications for XAI deployment where practitioners must validate ML predictions.

翻译：硬件木马检测需要准确的识别和可解释的说明，以便安全工程师验证结果并采取行动。本研究在Trust-Hub基准测试上比较了门级木马检测的三种可解释性方法类别：（1）基于领域知识的属性分析，通过门扇入模式、触发器距离和输入/输出连接性提取31个电路特定特征；（2）基于案例的推理，使用k近邻算法提供基于先例的解释；（3）与模型无关的特征归因方法（LIME、SHAP、梯度法）。结果显示各类方法具有不同优势。基于属性的分析通过电路概念提供解释，例如“输出端附近的高扇入复杂度可能指示潜在触发器”。基于案例的推理在预测结果与训练样本之间达到97.4%的对应度，提供基于先例的论证依据。LIME和SHAP提供的特征归因具有强跨方法相关性（r=0.94，p<0.001），但缺乏电路层面的验证背景。在11,392个测试样本上，XGBoost分类器实现了46.15%的精确率和52.17%的召回率，较先前研究（Hasegawa等人：5.13%）将精确率提升9倍，同时将误报率从5.6%降至0.25%。基于梯度的归因方法运行速度比SHAP快481倍，但提供类似的领域不透明洞察。本研究表明，相较于通用的特征排序方法，基于属性和基于案例的方法能提供更好的领域对齐和基于先例的可解释性，这对需要从业者验证机器学习预测结果的XAI部署具有重要启示。