Backdoor attacks against deep image compression via adaptive frequency trigger
Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable to backdoor attacks, where some specific trigger patterns added to the input can lead to malicious behavior of the models...
Saved in:
Main Authors: | Yu, Yi, Wang, Yufei, Yang, Wenhan, Lu, Shijian, Tan, Yap Peng, Kot, Alex Chichung |
---|---|
Other Authors: | Interdisciplinary Graduate School (IGS) |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/168045 https://cvpr2023.thecvf.com/Conferences/2023 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Robustness of semi-supervised deep learning model against backdoor attacks
by: Siew, Jun Ze
Published: (2023) -
Efficient and secure federated learning against backdoor attacks
by: MIAO, Yinbin, et al.
Published: (2024) -
Deepfake based backdoor attack against face recognition deep neural networks
by: Tan, Davis Wen Han
Published: (2023) -
Lossy intermediate deep learning feature compression and evaluation
by: Chen, Zhuo, et al.
Published: (2020) -
Exposing video compression history by detecting transcoded HEVC videos from AVC coding
by: Bian, Shan, et al.
Published: (2019)