A sparse adversarial attack that optimizes a mask over an I-FGSM perturbation, using a Gaussian-smoothed Heaviside step to approximate the L0 penalty, achieves sparser and faster attacks and attributes misclassification to obscuring and leading noise.
Enabling scalable and adaptive machine learning training via serverless computing on public cloud.Performance Evaluation, 167:102451, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Interpretable Adversarial Examples via Sparse Adversarial Attack
A sparse adversarial attack that optimizes a mask over an I-FGSM perturbation, using a Gaussian-smoothed Heaviside step to approximate the L0 penalty, achieves sparser and faster attacks and attributes misclassification to obscuring and leading noise.