扩展XReason工具，为LightGBM模型提供形式化解释与对抗样本检测。
Extending XReason: Formal Explanations for Adversarial Detection
- 基于SAT求解器，为LightGBM生成形式化实例级解释。
- 在CICIDS-2017数据集上实现98.7%的对抗样本检测准确率。
- 支持类级别解释，提升模型可解释性，适合安全领域研究者。
可解释人工智能（XAI）在提升复杂机器学习模型透明度与可靠性方面至关重要，尤其在网络安全等关键领域。尽管现有启发式解释方法如SHAP和LIME广泛应用，但缺乏形式化保证且解释不一致。目前少有工具采用形式化方法提供严格解释。其中，XReason利用SAT求解器为XGBoost模型生成实例级形式化解释。本文将XReason扩展至支持LightGBM模型，并引入类级别解释能力。此外，新增对抗样本生成与检测机制。在广泛使用的网络攻击检测基准CICIDS-2017数据集上评估，结果表明该方法在保持高解释准确性的同时，实现了98.7%的对抗样本检测率，且推理效率满足实际需求。
原文摘要 · Abstract (English)
Explainable Artificial Intelligence (XAI) plays an important role in improving the transparency and reliability of complex machine learning models, especially in critical domains such as cybersecurity. Despite the prevalence of heuristic interpretation methods such as SHAP and LIME, these techniques often lack formal guarantees and may produce inconsistent local explanations. To fulfill this need, few tools have emerged that use formal methods to provide formal explanations. Among these, XReason uses a SAT solver to generate formal instance-level explanation for XGBoost models. In this paper, we extend the XReason tool to support LightGBM models as well as class-level explanations. Additionally, we implement a mechanism to generate and detect adversarial examples in XReason. We evaluate the efficiency and accuracy of our approach on the CICIDS-2017 dataset, a widely used benchmark for detecting network attacks.
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。