| Title | MT-MTD: Muti-Training based Moving Target Defense Trojaning Attack in Edged-AI network |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Qiu, Yihao, Wu, Jun, Mumtaz, Shahid, Li, Jianhua, Al-Dulaimi, Anwer, Rodrigues, Joel J. P. C. |
| Conference Name | ICC 2021 - IEEE International Conference on Communications |
| Keywords | Conferences, Deep Learning, Deep Neural Network, Edged-AI, Games, Hardware, Image edge detection, Metrics, moving target defense, pubcrawl, resilience, Resiliency, Scalability, simulation, Training, Trojaning attack |
| Abstract | The evolution of deep learning has promoted the popularization of smart devices. However, due to the insufficient development of computing hardware, the ability to conduct local training on smart devices is greatly restricted, and it is usually necessary to deploy ready-made models. This opacity makes smart devices vulnerable to deep learning backdoor attacks. Some existing countermeasures against backdoor attacks are based on the attacker's ignorance of defense. Once the attacker knows the defense mechanism, he can easily overturn it. In this paper, we propose a Trojaning attack defense framework based on moving target defense(MTD) strategy. According to the analysis of attack-defense game types and confrontation process, the moving target defense model based on signaling game was constructed. The simulation results show that in most cases, our technology can greatly increase the attack cost of the attacker, thereby ensuring the availability of Deep Neural Networks(DNN) and protecting it from Trojaning attacks. |
| DOI | 10.1109/ICC42927.2021.9500545 |
| Citation Key | qiu_mt-mtd_2021 |
MT-MTD: Muti-Training based Moving Target Defense Trojaning Attack in Edged-AI network