Across 240 model configurations and 13 attacks, adaptive and curriculum adversarial training give the largest robustness gains, but 20.53% of evaluations show negative gains, mostly under mismatched source-target models and low-severity attacks.
In: European conference on computer vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DUMB and DUMBer: Is Adversarial Training Worth It in the Real World?
Across 240 model configurations and 13 attacks, adaptive and curriculum adversarial training give the largest robustness gains, but 20.53% of evaluations show negative gains, mostly under mismatched source-target models and low-severity attacks.