Adversarial Attacks on the Interpretation of Neuron Activation Maximization.
Géraldin NanfackAlexander FulleringerJonathan MartyMichael EickenbergEugene BelilovskyPublished in: AAAI (2024)
Keyphrases
- neural network
- countermeasures
- objective function
- information processing
- multi agent
- malicious users
- biologically inspired
- semantic interpretation
- cooperative
- image watermarking
- malicious attacks
- associative memory
- watermarking scheme
- image interpretation
- security mechanisms
- computer security
- traffic analysis
- denial of service attacks
- attack detection