Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing.
Zhen XiangDavid J. MillerGeorge KesidisPublished in: CoRR (2020)
Keyphrases
- reverse engineering
- neural network
- training set
- software engineering
- watermarking scheme
- malicious code
- software maintenance
- dynamic analysis
- gene regulatory networks
- object oriented
- attack detection
- conceptual schema
- business rules
- computer aided design
- test set
- artificial neural networks
- reverse engineer
- data sets
- database systems
- software evolution
- supervised learning
- watermarking technique
- training data