A Feasibility Study of Data Poisoning against On-device Learning Edge AI by Physical Attack against Sensors
Authors:
Open Access
- 1 July 2024
- journal article
- research article
- Published by Research Institute of Signal Processing, Japan in Journal of Signal Processing
- Vol. 28 (4) , 107-110
Abstract
In this paper, we examine security for edge AI devices that detect anomaly behavior due to machine failures. Typical edge AI devices perform only inference, but the inference accuracy may be degraded when sensing data changes depending on the environment in which the devices are deployed. One countermeasure against this problem is on-device learning, in which an AI updates its learning model in accordance with its environment. However, on-device learning AIs face a variety of security threats: for example, the correct inference cannot be performed if the deployed AI model is manipulated by the attacker. Although threats including invasive/non-invasive attacks via physical access have been mentioned in the past, relatively few reports have investigated experimental attacks. In this work, we demonstrated data poisoning by exploiting physical attacks on sensors implemented on edge AI. A system for detecting abnormal vibrations was evaluated using an autoencoder that utilizes sensing data from an accelerometer attached to a cooling fan as input. Accelerometer values can be tampered with during an acoustic wave injection attack, so we exploited this kind of attack. The anomaly detector that learned the tampered data could not detect abnormal fan vibrations correctly.Keywords
This publication has 5 references indexed in Scilit:
- Hardware Security on Edge AI DevicesIEICE ESS Fundamentals Review, 2021
- A Neural Network-Based On-device Learning Anomaly Detector for Edge DevicesIEEE Transactions on Computers, 2020
- WALNUT: Waging Doubt on the Integrity of MEMS Accelerometers with Acoustic Injection Attacks2017
- Bagging Classifiers for Fighting Poisoning Attacks in Adversarial Classification Tasks2011
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006