Crafting Adversarial Examples for Deep Learning Based Prognostics (Extended Version)

Abstract

In manufacturing, unexpected failures are considered a primary operational risk, as they can hinder productivity and can incur huge losses. State-of-the-art Prognostics and Health Management (PHM) systems incorporate Deep Learning (DL) algorithms and Internet of Things (IoT) devices to ascertain the health status of equipment, and thus reduce the downtime, maintenance cost and increase the productivity. Unfortunately, IoT sensors and DL algorithms, both are vulnerable to cyber attacks, and hence pose a significant threat to PHM systems. In this paper, we adopt the adversarial example crafting techniques from the computer vision domain and apply them to the PHM domain. Specifically, we craft adversarial examples using the Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM) and apply them on the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN) based PHM models. We evaluate the impact of adversarial attacks using NASA's turbofan engine dataset. The obtained results show that all the evaluated PHM models are vulnerable to adversarial attacks and can cause a serious defect in the remaining useful life estimation. The obtained results also show that the crafted adversarial examples are highly transferable and may cause significant damages to PHM systems.

RES-HD: Resilient Intelligent Fault Diagnosis Against Adversarial Attacks Using Hyper-Dimensional Computing

“…These attacks are dangerous since data analytics is an indispensable part of I-IoT systems. They can result in serious outcomes, e.g., undetected failures in a system [10].…”

“…There are various IFD methods, such as convolutional neural network (CNN) [6], long short-term memory (LSTM) [7], gated recurrent unit (GRU) [8], ensemble learning [9], etc. However, adversarial attacks against deployed ML models can lead to serious consequences for a PDM system such as delayed maintenance or replacement of a machine [10]. Mode and Hoque [10] analyze the impact of different adversarial attacks against ML for remaining useful life (RUL) prediction.…”

“…However, adversarial attacks against deployed ML models can lead to serious consequences for a PDM system such as delayed maintenance or replacement of a machine [10]. Mode and Hoque [10] analyze the impact of different adversarial attacks against ML for remaining useful life (RUL) prediction. They implement Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM) to craft adversarial examples and compare different DL model performances under those attacks.…”

“…Adversarial attacks against ML methods manipulate legitimate inputs and force the trained model to produce incorrect outputs leading to incorrect predictions. Since ML is in the center of intelligent fault diagnosis, these attacks may have serious consequences such as undetected failures [10]. There is a need for novel intelligent learning solutions that can stay resilient against various adversarial attacks.…”