With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life. Neural network or artificial neural network (NN), the main technique behind DL, has been extensively studied to facilitate computer vision and natural language recognition. However, the more we rely on information technology, the more vulnerable we are. That is, malicious NNs could bring huge threat in the so-called coming AI era. In this paper, for the first time in the literature, we propose a novel approach to design and insert powerful neural-level trojans or PoTrojan in pre-trained NN models. Most of the time, PoTrojans remain inactive, not affecting the normal functions of their host NN models. PoTrojans could only be triggered in very rare conditions. Once activated, however, the PoTrojans could cause the host NN models to malfunction, either falsely predicting or classifying, which is a significant threat to human society of the AI era. We would explain the principles of PoTrojans and the easiness of designing and inserting them in pre-trained deep learning models. PoTrojans doesn't modify the existing architecture or parameters of the pre-trained models, without re-training. Hence, the proposed method is very efficient.
[1]
Wen-Chuan Lee,et al.
Trojaning Attack on Neural Networks
,
2018,
NDSS.
[2]
Dawn Song,et al.
Robust Physical-World Attacks on Deep Learning Models
,
2017,
1707.08945.
[3]
Michael S. Bernstein,et al.
ImageNet Large Scale Visual Recognition Challenge
,
2014,
International Journal of Computer Vision.
[4]
Andrew Zisserman,et al.
Very Deep Convolutional Networks for Large-Scale Image Recognition
,
2014,
ICLR.
[5]
Yoshua Bengio,et al.
Generative Adversarial Networks
,
2014,
ArXiv.
[6]
Farinaz Koushanfar,et al.
A Survey of Hardware Trojan Taxonomy and Detection
,
2010,
IEEE Design & Test of Computers.
[7]
Yan Liu,et al.
Deep residual learning for image steganalysis
,
2018,
Multimedia Tools and Applications.
[8]
Geoffrey E. Hinton,et al.
ImageNet classification with deep convolutional neural networks
,
2012,
Commun. ACM.
[9]
Arturo Geigel,et al.
Neural network Trojan
,
2013,
J. Comput. Secur..
[10]
Brendan Dolan-Gavitt,et al.
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
,
2017,
ArXiv.
[11]
Demis Hassabis,et al.
Mastering the game of Go with deep neural networks and tree search
,
2016,
Nature.