This paper investigates the robustness of deep image super-resolution models using normalizing flow against adversarial attacks. Attack methods specific to flow-based super-resolution models are formulated, and the performance and influences of the attacks are analyzed. We show that flow-based super-resolution models are highly vulnerable to attacks, which are even more serious than other super-resolution models. Potential remedies to the vulnerability are also evaluated.
|Title of host publication||2022 IEEE 24th International Workshop on Multimedia Signal Processing, MMSP 2022|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Publication status||Published - 2022|
|Event||24th IEEE International Workshop on Multimedia Signal Processing, MMSP 2022 - Shanghai, China|
Duration: 2022 Sept 26 → 2022 Sept 28
|Name||2022 IEEE 24th International Workshop on Multimedia Signal Processing, MMSP 2022|
|Conference||24th IEEE International Workshop on Multimedia Signal Processing, MMSP 2022|
|Period||22/9/26 → 22/9/28|
Bibliographical noteFunding Information:
This work was supported by the NRF grant funded by the Korea government (MSIT) (2021R1A2C2011474).
© 2022 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Signal Processing
- Media Technology