选择性增强和扩充预测器的鲁棒集成
Robust Ensemble of Selectively Strengthened and Augmented Predictors
AI总结:
提出RESSAP框架,通过将单一分类器转化为基于特征子集选择的鲁棒集成,并采用随机子集投票和噪声数据增强,显著提升对抗逃避攻击的鲁棒性。
摘要:
逃避攻击对基于机器学习的分类器的鲁棒性构成了重大挑战,尤其是在欺诈检测和网络安全等关键应用中。尽管现有的防御机制在某些设置下有效,但它们通常泛化能力有限,并且不能系统地提高模型在不同攻击场景下的鲁棒性。为了解决这些局限性,我们引入了选择性增强和扩充预测器的鲁棒集成(RESSAP),这是一种将单一分类器转化为鲁棒分类器集成的新框架。集成中的每个分类器都在精心选择的特征子集上训练,其中特征选择由同时考虑特征重要性和鲁棒性的弹性度量指导。在推理过程中,使用这些分类器的随机子集进行预测,增加了不可预测性并提高了对对抗性操纵的抵抗力。此外,在训练过程中应用基于噪声的数据增强来加强决策边界并改善泛化能力。我们的实验结果表明,RESSAP在保持对干净数据的高准确性的同时,显著提高了对对抗性逃避攻击的鲁棒性。总体而言,这个模型无关的框架提供了一种可扩展且灵活的防御策略,用于增强机器学习系统的安全性,而无需对现有架构进行重大更改。
英文摘要:
Evasion attacks present a significant challenge to the robustness of machine learning (ML)-based classifiers, particularly in critical applications such as fraud detection and cybersecurity. Although existing defense mechanisms are effective in some settings, they often suffer from limited generalizability and do not systematically improve model robustness across diverse attack scenarios. To address these limitations, we introduce Robust Ensemble of Selectively Strengthened and Augmented Predictors (RESSAP), a novel framework that transforms a single classifier into an ensemble of robust classifiers. Each classifier in the ensemble is trained on a carefully selected subset of features, where feature selection is guided by a resilience metric that accounts for both feature importance and robustness. During inference, a random subset of these classifiers is used to make predictions, increasing unpredictability and improving resistance to adversarial manipulation. In addition, noise-based data augmentation is applied during training to strengthen decision boundaries and improve generalization. Our experimental results demonstrate that RESSAP significantly improves robustness against adversarial evasion attacks while maintaining strong accuracy on clean data. Overall, this model-agnostic framework provides a scalable and flexible defense strategy for enhancing the security of machine learning systems without requiring major changes to existing architectures.
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。