An Assessment of Robustness for Adversarial Attacks and Physical Distortions on Image Classification using Explainable AI.
K. T. Yasas MahimaMohamed AyoobGuhanathan PoraviPublished in: AI-Cybersec@SGAI (2021)
Keyphrases
- image classification
- artificial intelligence
- digital image watermarking
- image watermarking scheme
- feature extraction
- expert systems
- semi fragile watermarking
- bag of words
- image features
- intelligent systems
- geometric attacks
- geometric distortions
- case based reasoning
- machine learning
- countermeasures
- visual words
- sparse representation
- malicious attacks
- multiscale
- knowledge representation
- physical world
- traffic analysis
- image representation
- watermarking scheme
- multi agent
- watermarking algorithm
- security mechanisms
- ai systems
- security threats
- ai methods
- computer vision