papers AI Learner
The Github is limit! Click to go to the new site.

A Provable Defense for Deep Residual Networks

2019-03-29
Matthew Mirman, Gagandeep Singh, Martin Vechev

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.12519

PDF

http://arxiv.org/pdf/1903.12519


Similar Posts

Comments