End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery
Researchers show end-to-end hard-label extraction of small ReLU MLPs, exceeding 98% label agreement on MNIST.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #hard-label
Normal Alignment: Improved Cryptanalytic Sign Recovery on Hard-Label Networks
Researchers propose Normal Alignment, improving cryptanalytic sign recovery for hard-label neural networks and enabling polynomial-time full model extraction.