Regression models are widely used in industrial processes, engineering and in natural and physical sciences, yet their robustness to poisoning has received less attention. When it has, studies often assume unrealistic threat models and are thus less useful in practice. In this paper, we propose a novel optimal stealthy attack formulation that considers different degrees of detectability and show that it bypasses state-of-the-art defenses. We further propose a new methodology based on normalization of objectives to evaluate different trade-offs between effectiveness and detectability. Finally, we develop a novel defense (BayesClean) against stealthy attacks. BayesClean improves on previous defenses when attacks are stealthy and the number of poisoning points is significant.

翻译：回归模型在工业流程、工程领域以及自然科学与物理学中广泛应用，然而其对于投毒攻击的鲁棒性却较少受到关注。即便有所研究，现有工作通常基于不切实际的威胁模型，因而在实践中实用性有限。本文提出了一种新颖的最优隐蔽攻击建模方法，该方法考虑了不同程度的可检测性，并证明其能够规避当前最先进的防御机制。我们进一步提出了一种基于目标归一化的新方法论，用以评估攻击有效性与可检测性之间的不同权衡关系。最后，我们针对隐蔽攻击开发了一种新型防御方法（BayesClean）。当攻击具有隐蔽性且投毒数据点数量较大时，BayesClean相较于现有防御方法展现出显著改进。