Learning to Generate Inversion-Resistant Model Explanations
–Neural Information Processing Systems
Figure 1 compares the result of MI attacks using model predictions alone (PredMI) and explanation-aware MI attacks using model predictions and explanations together (ExpMI).
Neural Information Processing Systems
Feb-9-2026, 17:56:40 GMT
- Country:
- North America > Canada > Ontario > Toronto (0.14)
- Genre:
- Research Report > New Finding (0.94)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology: