Search Results for author:
Found 3 papers, 0 papers with code
Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers
Clean-label settings make the attack more stealthy due to the correct image-label pairs, but some problems still exist: first, traditional methods for poisoning training data are ineffective; second, traditional triggers are not stealthy which are still perceptible.
Boosting Adversarial Transferability of MLP-Mixer
Our method can mask the part input of the Mixer layer, avoid overfitting of the adversarial examples to the source model, and improve the transferability of cross-architecture.
Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity
Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
