🧪 Test?View on arXiv
Density Feedback Control for Transferability of Generative Sparse Adversarial Attacks
Not provided in the content
adversarial attacksdensity controltransferabilityneural networks
2611.25001
Builder Relevance
2d ago70%
Abstract
The paper proposes Density Feedback Control (DFC) to improve the transferability of sparse adversarial attacks by adjusting the sparsity coefficient based on the observed density.
Reality Card
Core Claim
DFC achieves a mean density within one percentage point of the target density and improves the transfer attack success rate on CNN and Transformer targets while perturbing fewer pixels.
Method / Result
At a 10% target density, DFC improves transfer attack success rate (ASR) and reduces the number of perturbed pixels.
Limitations
The method's performance may vary based on the interaction between density feedback and restrictions on perturbations.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.