arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12959cs.LGcs.CR
收藏

基于混沌变分自动编码器的对抗性机器学习

Chaotic Variational Auto encoder-based Adversarial Machine Learning

School of Computer Science And Information Sciences, University of Hyderabad(海得拉巴大学计算机科学与信息科学学院)

Pavan Venkata Sainadh Reddy, Yelleti Vivek, Gopi Pranay, Vadlamani Ravi

摘要:

机器学习(Machine Learning,ML)已经成为几乎所有领域的新发明。这使得它们成为各种对手攻击的欺诈者的目标,从而阻碍了ML模型的性能。规避和基于数据毒药的攻击备受好评,特别是在金融,医疗保健等领域,这促使我们提出了一种新的计算成本较低的攻击机制,基于变分自动编码器(VAE)的对抗性样本生成。众所周知,小波神经网络(WNN)被认为是计算效率高的解决图像和音频处理,语音识别,和时间序列预测。提出了一种基于小波神经网络的VAE-深度小波神经网络(VAE-Deep-WNN)。此外,我们提出了VAE与多层感知器(MLP)和Deep-WNN的混沌变体,并分别命名为C-VAE-MLP和C-VAE-Deep-WNN。在这里,我们使用Logistic映射在潜在空间中生成随机噪声。在本文中,我们执行了基于VAE的对手样本生成,并将其应用于与金融和网络安全领域相关的各种问题,如贷款违约,信用卡欺诈和流失建模等,我们对逻辑回归(LR)和决策树(DT)模型进行了规避和数据中毒攻击。结果表明,VAE-Deep-WNN在大多数数据集和模型中的表现优于其他模型。然而,其混沌变体C-VAE-Deep-WNN在大多数数据集中的表现几乎与VAE-Deep-WNN相似。

英文摘要:

Machine Learning (ML) has become the new contrivance in almost every field. This makes them a target of fraudsters by various adversary attacks, thereby hindering the performance of ML models. Evasion and Data-Poison-based attacks are well acclaimed, especially in finance, healthcare, etc. This motivated us to propose a novel computationally less expensive attack mechanism based on the adversarial sample generation by Variational Auto Encoder (VAE). It is well known that Wavelet Neural Network (WNN) is considered computationally efficient in solving image and audio processing, speech recognition, and time-series forecasting. This paper proposed VAE-Deep-Wavelet Neural Network (VAE-Deep-WNN), where Encoder and Decoder employ WNN networks. Further, we proposed chaotic variants of both VAE with Multi-layer perceptron (MLP) and Deep-WNN and named them C-VAE-MLP and C-VAE-Deep-WNN, respectively. Here, we employed a Logistic map to generate random noise in the latent space. In this paper, we performed VAE-based adversary sample generation and applied it to various problems related to finance and cybersecurity domain-related problems such as loan default, credit card fraud, and churn modelling, etc., We performed both Evasion and Data-Poison attacks on Logistic Regression (LR) and Decision Tree (DT) models. The results indicated that VAE-Deep-WNN outperformed the rest in the majority of the datasets and models. However, its chaotic variant C-VAE-Deep-WNN performed almost similarly to VAE-Deep-WNN in the majority of the datasets.

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。

↑