.png){kind=icon}
返回
Dynamic Deep Neural Network Adversarial Attacks for Edge-based IoT Devices
.png){kind=icon}
PRE
AI
DOI：10.1109/GLOBECOM48099.2022.10001235.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Edge-based IoT devices have experienced phenomenal growth in recent years due to rapidly increasing demand in various emerging applications which typically utilize machine learning (ML) models such as Deep Neural Network (DNN) and demand low latency and low power consumption. To support the edge requirements, ML models have to support faster inference and less computation. Dynamic DNNs (D2NN) have been proposed to support low-latency and power-saving on edge devices by enabling conditional computations and context dependant activation of the network model for inference; saving computational time and edge resources, hence they are becoming popular for edge applications. In this paper, we show that D2NN are vulnerable to our novel adversarial attack, Dynamic DNN Adversarial attacks (DDAS). Unlike conventional adversarial attacks that target classification accuracy, DDAS targets the IoT device resources such as the battery, latency, and so on. We show that our attack is effective under various attack scenarios with a high attack success rate. We also provide a retraining scheme as a countermeasure to DDAS and show its effectiveness.
Keyword:
Adversarial Attack
Classification
IoT
期刊
I
IF:
0
论文数:
44
被引数:
0
机构
引用论文
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏FOLLOW-UP: THE BACTERIAL ETIOLOGY AND ANTIBIOTIC MANAGEMENT OF SEPTIC ARTHRITIS IN INFANTS AND CHILDREN.png)
Pediatrics
PediatricsIF0
PREAI
分享收藏
查看更多内容