通过机器学习可解释性研究软件分析中的对抗攻击
Investigating Adversarial Attacks in Software Analytics via Machine Learning Explainability
AI总结：
本研究通过机器学习可解释性探索软件分析中的对抗攻击，提出基于特征空间扰动的方法，仅修改前1-3个重要特征即可使模型预测失败率达86.6%，揭示了模型鲁棒性不足的问题。
摘要：
随着机器学习（ML）的最新进展，许多基于ML的方法已广泛应用于软件分析任务中，以简化软件开发和维护过程。然而，研究表明，尽管ML模型具有潜在的实用性，但它们容易受到对抗攻击，这可能导致这些过程出现重大的经济损失。因此，在将ML模型部署到软件分析任务之前，必须评估它们对对抗攻击的鲁棒性。尽管已有几种用于软件分析任务中对抗攻击的技术，但使用ML可解释性来探索对抗攻击在很大程度上仍未被探索。因此，本研究旨在调查ML可解释性与对抗攻击之间的关系，以衡量ML模型在软件分析任务中的鲁棒性。此外，与大多数直接扰动输入空间的现有攻击不同，我们的攻击方法侧重于扰动特征空间。我们进行了广泛的实验，涉及六个数据集、三种ML可解释性技术和七个ML模型，结果表明ML可解释性可用于对软件分析任务中的ML模型进行成功的对抗攻击。这是通过仅修改由ML可解释性技术识别的前1-3个重要特征来实现的。因此，受到攻击的ML模型无法准确预测高达86.6%在对抗攻击之前被正确预测的实例，表明模型对此类攻击的鲁棒性较低。最后，与针对表格数据的四种最先进的对抗攻击技术相比，我们提出的技术展示了有希望的结果。
英文摘要：
With the recent advancements in machine learning (ML), numerous ML-based approaches have been extensively applied in software analytics tasks to streamline software development and maintenance processes. Nevertheless, studies indicate that despite their potential usefulness, ML models are vulnerable to adversarial attacks, which may result in significant monetary losses in these processes. As a result, the ML models' robustness against adversarial attacks must be assessed before they are deployed in software analytics tasks. Despite several techniques being available for adversarial attacks in software analytics tasks, exploring adversarial attacks using ML explainability is largely unexplored. Therefore, this study aims to investigate the relationship between ML explainability and adversarial attacks to measure the robustness of ML models in software analytics tasks. In addition, unlike most existing attacks that directly perturb input-space, our attack approach focuses on perturbing feature-space. Our extensive experiments, involving six datasets, three ML explainability techniques, and seven ML models, demonstrate that ML explainability can be used to conduct successful adversarial attacks on ML models in software analytics tasks. This is achieved by modifying only the top 1-3 important features identified by ML explainability techniques. Consequently, the ML models under attack fail to accurately predict up to 86.6% of instances that were correctly predicted before adversarial attacks, indicating the models' low robustness against such attacks. Finally, our proposed technique demonstrates promising results compared to four state-of-the-art adversarial attack techniques targeting tabular data.
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。
