Sparse Backdoor plants a provably undetectable backdoor in neural network weights via structured sparse perturbations and isotropic Gaussian dithering, with detection hardness reduced to Sparse PCA.
Spectral signatures in backdoor attacks.Advances in neural information processing systems, 31, 2018
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces a text-guided backdoor attack using common textual words as triggers and visual perturbations for stealthy, adjustable control on multimodal pretrained models.
citing papers explorer
-
Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
Sparse Backdoor plants a provably undetectable backdoor in neural network weights via structured sparse perturbations and isotropic Gaussian dithering, with detection hardness reduced to Sparse PCA.
-
Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models
Introduces a text-guided backdoor attack using common textual words as triggers and visual perturbations for stealthy, adjustable control on multimodal pretrained models.