A Provable Defense for Deep Residual Networks

03/29/2019
by   Matthew Mirman, et al.
0

We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100. Our approach is based on differentiable abstract interpretation and introduces two novel concepts: (i) abstract layers for fine-tuning the precision and scalability of the abstraction, (ii) a flexible domain specific language (DSL) for describing training objectives that combine abstract and concrete losses with arbitrary specifications. Our training method is implemented in the DiffAI system.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset