用线性权重分类解决木马检测竞赛
Solving Trojan Detection Competitions with Linear Weight Classification
AI总结：
本文提出一种基于线性权重分类的木马检测器，通过对模型权重进行预处理后训练二元分类器，在多个基准上表现优异。
摘要：
神经网络可以隐藏恶意的木马后门，使得触发器能够隐蔽地改变模型行为。检测这些后门的迹象，尤其是在没有任何触发数据的情况下，是当前研究和开放挑战的主题。在该问题的一种常见表述中，我们得到一组干净和被污染的模型，需要预测给定的测试模型是干净的还是被污染的。在本文中，我们引入了一种检测器，它在许多现有数据集和领域中表现非常出色。该检测器通过对大量模型的权重进行几种不同的预处理步骤（包括特征选择和标准化、参考模型权重减法以及检测前的模型对齐）后训练一个二元分类器而获得。我们在多样化的木马检测基准和领域上评估了该算法，并考察了该方法最有效和最无效的情况。
英文摘要：
Neural networks can conceal malicious Trojan backdoors that allow a trigger to covertly change the model behavior. Detecting signs of these backdoors, particularly without access to any triggered data, is the subject of ongoing research and open challenges. In one common formulation of the problem, we are given a set of clean and poisoned models and need to predict whether a given test model is clean or poisoned. In this paper, we introduce a detector that works remarkably well across many of the existing datasets and domains. It is obtained by training a binary classifier on a large number of models' weights after performing a few different pre-processing steps including feature selection and standardization, reference model weights subtraction, and model alignment prior to detection. We evaluate this algorithm on a diverse set of Trojan detection benchmarks and domains and examine the cases where the approach is most and least effective.
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。
