Compression acts as an adversarial amplifier by reducing the decision space of image classifiers, making attacks in compressed representations substantially more effective than pixel-space attacks under the same perturbation budget.
G., and Murray, R.Adversarial classification: Necessary conditions and geometric flows.Journal of Machine Learning Research 23, 187 (2022), 1–38
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compression as an Adversarial Amplifier Through Decision Space Reduction
Compression acts as an adversarial amplifier by reducing the decision space of image classifiers, making attacks in compressed representations substantially more effective than pixel-space attacks under the same perturbation budget.