Adversarial Knowledge
Adversarial knowledge refers to the prior information an attacker possesses about the target model or data distribution when performing membership inference attacks, typically including model architecture, hyperparameters, training algorithms, output confidence distributions, and even the training data of some shadow models. Depending on the degree of knowledge, attacks can be categorized into white-box, gray-box, and black-box types.
Timeline (last 90 days)
Experimental results show that advanced MIA methods are highly dependent on adversarial knowledge of the target model (such as model architecture, training hyperparameters, or output confidence distributions), and when this knowledge is limited, attack effectiveness drops noticeably.
Adversarial knowledge refers to the prior information an attacker possesses about the target model or data distribution when carrying out MIA, typically including model architecture, hyperparameters, training algorithm, output confidence distribution, and even the training data of some shadow models.
All Facts (2)
Experimental results show that advanced MIA methods are highly dependent on adversarial knowledge of the target model (such as model architecture, training hyperparameters, or output confidence distributions), and when this knowledge is limited, attack effectiveness drops noticeably.
50%UnverifiedAdversarial knowledge refers to the prior information an attacker possesses about the target model or data distribution when carrying out MIA, typically including model architecture, hyperparameters, training algorithm, output confidence distribution, and even the training data of some shadow models.
50%