Defense Against Image Captioning Attacks via A Robust and Stable Recurrent Neural Network.
Jiahuan ZhangKeisuke MaedaTakahiro OgawaMiki HaseyamaPublished in: GCCE (2021)
Keyphrases
- recurrent neural networks
- image noise
- image data
- multiscale
- image classification
- image content
- image features
- complex valued
- input image
- image retrieval
- neural network
- watermarking technique
- image watermarking
- single image
- image regions
- high resolution
- salt pepper
- image segmentation
- feed forward
- intrusion detection
- edge detection
- fuzzy neural network
- image matching
- feature points
- recurrent networks
- watermark detection
- robust watermarking scheme