all InfoSec news
Model Stealing Attack against Multi-Exit Networks. (arXiv:2305.13584v1 [cs.CR])
cs.CR updates on arXiv.org arxiv.org
Compared to traditional neural networks with a single exit, a multi-exit
network has multiple exits that allow for early output from intermediate layers
of the model, thus bringing significant improvement in computational efficiency
while maintaining similar recognition accuracy. When attempting to steal such
valuable models using traditional model stealing attacks, we found that
conventional methods can only steal the model's classification function while
failing to capture its output strategy. This results in a significant decrease
in computational efficiency for the …
accuracy attack attacks computational efficiency exit improvement network networks neural networks recognition single steal stealing