JPEG-resistant Adversarial Images
Several papers have explored the use of JPEG compression as a defense against adversarial images. In this work, we show that we can generate adversarial images which survive JPEG compression, by including a differentiable approximation to JPEG in the target model. By ensembling multiple target models employing varying levels of compression, we generate adversarial images with up to 691× greater success rate than the baseline method on a model using JPEG as defense.
PDFTasks
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
No methods listed for this paper. Add
relevant methods here