Exploring Security Vulnerabilities of Deep Learning Models by Adversarial Attacks

Abstract

Nowadays, deep learning models play an important role in a variety of scenarios, such as image classification, natural language processing, and speech recognition. However, deep learning models are shown to be vulnerable; a small change to the original data may affect the output of the model, which may incur severe consequences such as misrecognition and privacy leakage. The intentionally modified data is referred to as adversarial examples. In this paper, we explore the security vulnerabilities of deep learning models designed for textual analysis. Specifically, we propose a visual similar word replacement (VSWR) algorithm to generate adversarial examples against textual analysis models. By using adversarial examples as the input of deep learning models, we verified that deep learning models are vulnerable to such adversarial attacks. We have conducted experiments on several sentiment analysis deep learning models to evaluate the performance. The results also confirmed that the generated adversarial examples could successfully attack deep learning models. As the number of modified words increases, the model prediction accuracy becomes lower. This kind of adversarial attack implies security vulnerabilities of deep learning models.

Survey on Blockchain-Enhanced Machine Learning

“…These models have multiple layers; lower layers handle essential elements, and higher layers manage more abstract aspects. Notably, the number of layers in these models impacts their accuracy and security; increased complexity, as indicated by more layers, can make the models more susceptible to adversarial attacks, posing potential security risks [77].…”

Denoising by Decorated Noise: An Interpretability-Based Framework for Adversarial Example Detection

“…The continuous upgrading of DNNs provides an opportunity to efficiently process the enormous unstructured data generated by the wide-spreading imaging sensors in IoT systems [1,2]. However, recent studies [3][4][5] have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks, which apply subtle and unperceivable perturbations to input examples and can completely fool the deep learning model. According to different attack settings, adversarial attacks have developed various types of attacks, such as white-box attacks [6] and black-box attacks [7].…”