The basic idea is to hide a smaller image inside a larger image (it should be about 5-10x the size). The attack is easy to explain actually:
- Attacker crafts a malicious input image by hiding the desired target image inside a benign image
- The image is loaded by the server
- Pre-processing resizes the image -The server acts and makes decision based on a different image then intended
Some spiders pair puny males with gigantic females, making mating both tricky and dangerous. Why and how such mismatches evolved remains curiously enigmatic.
Source: The ungentle joy of spider sex, an article by Stephanie Pain.
Data Augmentation is a technique that can be used to artificially expand the size of a training set by creating modified data from the existing one. It is a good practice to use DA if you want to prevent overfitting, or the initial dataset is too small to train on, or even if you want to squeeze better performance from your model.
Source: Data Augmentation in Python: Everything You Need to Know, an article by Vladimir Lyashenko.