扩展 XReason：面向对抗检测的形式化解释
Extending XReason: Formal Explanations for Adversarial Detection
AI总结：
本文扩展 XReason 工具，使其支持 LightGBM 模型和类级形式化解释，并加入对抗样本生成与检测机制，在 CICIDS-2017 数据集上验证了方法的效率和准确性。
摘要：
可解释人工智能（XAI）在提高复杂机器学习模型的透明度和可靠性方面发挥着重要作用，尤其是在网络安全等关键领域。尽管 SHAP 和 LIME 等启发式解释方法较为流行，但这些技术往往缺乏形式化保证，并且可能产生不一致的局部解释。为了满足这一需求，已有少数工具采用形式化方法来提供形式化解释。其中，XReason 使用 SAT 求解器为 XGBoost 模型生成形式化的实例级解释。在本文中，我们扩展了 XReason 工具，使其支持 LightGBM 模型以及类级解释。此外，我们实现了一种在 XReason 中生成和检测对抗样本的机制。我们在 CICIDS-2017 数据集（一个广泛用于网络攻击检测的基准）上评估了所提方法的效率和准确性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
