ROI coding enables backdoor triggers to survive lossy compression by embedding malicious information into binary bitstreams via sample-specific or customized masks for both learned and traditional codecs.
Learned image compression with discretized gaussian mixture likelihoods and attention modules
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
BADiff introduces joint training of diffusion models with quality conditioning derived from bandwidth to enable adaptive early-stop sampling that preserves appropriate perceptual quality.
citing papers explorer
-
Inevitable Encounters: Backdoor Attacks Involving Lossy Compression
ROI coding enables backdoor triggers to survive lossy compression by embedding malicious information into binary bitstreams via sample-specific or customized masks for both learned and traditional codecs.
-
BADiff: Bandwidth Adaptive Diffusion Model
BADiff introduces joint training of diffusion models with quality conditioning derived from bandwidth to enable adaptive early-stop sampling that preserves appropriate perceptual quality.