Maximum Mean Discrepancy is Aware of Adversarial Attacks.

Ruize Gao Feng Liu Jingfeng Zhang Bo Han Tongliang Liu Gang Niu Masashi Sugiyama

Published in: CoRR (2020)

Keyphrases

traffic analysis
multi agent
terrorist attacks
neural network
website
malicious users
malicious attacks
security risks
chosen plaintext
real time
image watermarking
security protocols
watermarking technique
maximum number
watermarking algorithm
countermeasures
signal processing
case study
search engine