T-BFA: Targeted Bit-Flip Adversarial Weight Attack
- 16 September 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (11) , 7928-7939
Abstract
Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack. Recently, another dimension of adversarial attack, namely, attack on DNN weight parameters, has been shown to be very powerful. As a representative one, the Bit-Flip-based adversarial weight Attack (BFA) injects an extremely small amount of faults into weight parameters to hijack the executing DNN function. Prior works of BFA focus on un-targeted attack that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory. This paper proposes the first work of targeted BFA based (T-BFA) adversarial weight attack on DNNs, which can intentionally mislead selected inputs to a target output class. The objective is achieved by identifying the weight bits that are highly associated with classification of a targeted output through a class-dependent vulnerable weight bit searching algorithm. Our proposed T-BFA performance is successfully demonstrated on multiple DNN architectures for image classification tasks. For example, by merely flipping 27 out of 88 million weight bits of ResNet-18, our T-BFA can misclassify all the images from ’Hen’ class into ’Goose’ class (i.e., 100% attack success rate) in ImageNet dataset, while maintaining 59.35% validation accuracy. Moreover, we successfully demonstrate our T-BFA attack in a real computer prototype system running DNN computation, with Ivy Bridge-based Intel i7 CPU and 8GB DDR3 memory.Keywords
All Related Versions
Funding Information
- National Science Foundation (1931871, 2019536, 2019548)
This publication has 24 references indexed in Scilit:
- ZOO2017
- Fault injection attack on deep neural network2017
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Towards Evaluating the Robustness of Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- Deep Neural Language Models for Machine Translation2015
- Flipping bits in memory without accessing them: An experimental study of DRAM disturbance errors2014
- Fault Model Analysis of Laser-Induced Faults in SRAM Memory Cells2013
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012