arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1808.05705cs.CRstat.ML
收藏

通过嵌入式特征选择缓解对抗攻击

Mitigation of Adversarial Attacks through Embedded Feature Selection

Ziyi Bao, Luis Muñoz-González, Emil C. Lupu

摘要:

机器学习已经成为许多应用领域中任务自动化的主要组成部分之一。尽管机器学习取得了令人印象深刻的进步和成就,但已经表明,学习算法在训练和测试时都可能受到攻击者的影响。机器学习系统特别容易受到对抗性示例的影响,其中添加到原始数据点的小扰动可能在测试时在学习算法中产生不正确或意外的输出。缓解这些攻击是困难的,因为对抗性的例子很难检测到。现有的相关工作表明,当应用特征选择来降低系统的复杂度时,机器学习系统对对抗性样本的安全性会被削弱。在本文中,我们凭经验反驳了这一想法,表明攻击者必须引入成功的攻击的相对失真是更大的目标时,使用一组减少的功能。我们还表明,最小对抗性的例子在统计上与具有较低特征数量的真实例子有更大的差异。但是,减少功能数量可能会对系统性能产生负面影响。我们用具体的例子说明了安全性和准确性之间的权衡。我们提出了一种设计方法来评估嵌入特征选择的机器学习分类器对使用不同攻击策略制作的对抗性示例的安全性。

英文摘要:

Machine learning has become one of the main components for task automation in many application domains. Despite the advancements and impressive achievements of machine learning, it has been shown that learning algorithms can be compromised by attackers both at training and test time. Machine learning systems are especially vulnerable to adversarial examples where small perturbations added to the original data points can produce incorrect or unexpected outputs in the learning algorithms at test time. Mitigation of these attacks is hard as adversarial examples are difficult to detect. Existing related work states that the security of machine learning systems against adversarial examples can be weakened when feature selection is applied to reduce the systems' complexity. In this paper, we empirically disprove this idea, showing that the relative distortion that the attacker has to introduce to succeed in the attack is greater when the target is using a reduced set of features. We also show that the minimal adversarial examples differ statistically more strongly from genuine examples with a lower number of features. However, reducing the feature count can negatively impact the system's performance. We illustrate the trade-off between security and accuracy with specific examples. We propose a design methodology to evaluate the security of machine learning classifiers with embedded feature selection against adversarial examples crafted using different attack strategies.

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。

↑