The authors introduce I-FDGSM, an iterative adversarial attack that sets a target class probability to a specified value while keeping the true class dominant, and use it to verify whether a cloud model is the original model.
Turning your weakness into a strength: Watermarking deep neural networks by backdooring,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulation
The authors introduce I-FDGSM, an iterative adversarial attack that sets a target class probability to a specified value while keeping the true class dominant, and use it to verify whether a cloud model is the original model.