对比10种模型在恶意软件数据集上的抗标签翻转攻击能力，找出发现性能最稳的模型。
Robustness of Selected Learning Models under Label-Flipping Attack
- 通过故意篡改训练数据标签，测试各模型鲁棒性
- MLP在初始准确率和抗干扰能力上表现最优
- 为安全场景下的模型选型提供实证参考
本文对比了传统机器学习与深度学习模型在恶意软件数据集上面对标签翻转攻击时的鲁棒性。具体考察了支持向量机（SVM）、随机森林、高斯朴素贝叶斯（GNB）、梯度提升机（GBM）、LightGBM、XGBoost、多层感知机（MLP）、卷积神经网络（CNN）、MobileNet 和 DenseNet 在不同比例误导标签下的表现。通过实证评估各模型在对抗攻击下的准确率，研究旨在揭示哪些模型在训练数据被蓄意破坏时更具内在鲁棒性。实验结果显示各模型鲁棒性差异显著，其中多层感知机（MLP）在初始准确率与抗干扰能力之间取得了最佳平衡。
原文摘要 · Abstract (English)
In this paper we compare traditional machine learning and deep learning models trained on a malware dataset when subjected to adversarial attack based on label-flipping. Specifically, we investigate the robustness of Support Vector Machines (SVM), Random Forest, Gaussian Naive Bayes (GNB), Gradient Boosting Machine (GBM), LightGBM, XGBoost, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), MobileNet, and DenseNet models when facing varying percentages of misleading labels. We empirically assess the the accuracy of each of these models under such an adversarial attack on the training data. This research aims to provide insights into which models are inherently more robust, in the sense of being better able to resist intentional disruptions to the training data. We find wide variation in the robustness of the models tested to adversarial attack, with our MLP model achieving the best combination of initial accuracy and robustness.
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。