Search Results for author:
Found 6 papers, 1 papers with code
Towards Transferable Adversarial Attacks with Centralized Perturbation
To this end, we propose a transferable adversarial attack with fine-grained perturbation optimization in the frequency domain, creating centralized perturbation.
Unified High-binding Watermark for Unconditional Image Generation Models
In the first stage, we use an encoder to invisibly write the watermark image into the output images of the original AIGC tool, and reversely extract the watermark image through the corresponding decoder.
Artificial Intelligence Security Competition (AISC)
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems.
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.
Improving the Transferability of Adversarial Examples with Restructure Embedded Patches
We attack the unique self-attention mechanism in ViTs by restructuring the embedded patches of the input.
Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity
Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples.
