Stealthy and robust backdoor attack on deep neural networks based on data augmentation
This work proposes to use data augmentation for backdoor attacks to increase the stealth, attack success rate, and robustness. Different data augmentation techniques are applied independently on three color channels to embed a composite trigger. The data augmentation strength is tuned based on the G...
Saved in:
Main Authors: | Xu, Chaohui, Chang, Chip Hong |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/174145 https://ieee-ceda.org/event/2022-asian-hardware-oriented-security-and-trust-symposium |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
An imperceptible data augmentation based blackbox clean-label backdoor attack on deep neural networks
by: Xu, Chaohui, et al.
Published: (2024) -
Inconspicuous data augmentation based backdoor attack on deep neural networks
by: Xu, Chaohui, et al.
Published: (2023) -
Stealthy backdoor attack for code models
by: YANG, Zhou, et al.
Published: (2024) -
Stealthy and robust glitch injection attack on deep learning accelerator for target with variational viewpoint
by: Liu, Wenye, et al.
Published: (2021) -
Deep neural network-based bandwidth enhancement of photoacoustic data
by: Gutta, Sreedevi, et al.
Published: (2017)