Search Results for author:
Found 3 papers, 1 papers with code
Evaluating Adversarial Robustness in the Spatial Frequency Domain
Convolutional Neural Networks (CNNs) have dominated the majority of computer vision tasks.
In Anticipation of Perfect Deepfake: Identity-anchored Artifact-agnostic Detection under Rebalanced Deepfake Detection Protocol
To bridge this gap, we introduce the Rebalanced Deepfake Detection Protocol (RDDP) to stress-test detectors under balanced scenarios where genuine and forged examples bear similar artifacts.
Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial Attack
To improve efficiency, we introduce the limit-aware random gradient-free estimation and the gradient sliding mechanism to estimate the gradient that adheres to the adversarial limit, i. e., the pixel value limitations of the adversarial example.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
