A Provable Defense for Deep Residual Networks
Mirman, Matthew, Singh, Gagandeep, Vechev, Martin
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Mar-29-2019
- Country:
- Europe > Switzerland (0.14)
- Genre:
- Research Report > Promising Solution (0.34)
- Industry:
- Information Technology (0.46)
- Technology: