Search Results for author:
Found 2 papers, 0 papers with code
EZClone: Improving DNN Model Extraction Attack via Shape Distillation from GPU Execution Profiles
Prior work has shown that, once a DNN has been successfully cloned, further attacks such as model evasion or model inversion can be accelerated significantly.
Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning
The prevalence and success of Deep Neural Network (DNN) applications in recent years have motivated research on DNN compression, such as pruning and quantization.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
