Formal methods and software engineering for DL. Security, safety and productivity for DL systems development
arXiv:1901.11334
Abstract
Deep Learning (DL) techniques are now widespread and being integrated into many important systems. Their classification and recognition abilities ensure their relevance for multiple application domains. As machine-learning that relies on training instead of algorithm programming, they offer a high degree of productivity. But they can be vulnerable to attacks and the verification of their correctness is only just emerging as a scientific and engineering possibility. This paper is a major update of a previously-published survey, attempting to cover all recent publications in this area. It also covers an even more recent trend, namely the design of domain-specific languages for producing and training neural nets.
Submitted to IEEE-CCECE2019
References in corpus (12)
- NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
- Towards Proving the Adversarial Robustness of Deep Neural Networks
- A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees
- Relay: A New IR for Machine Learning Frameworks
- Provably Minimally-Distorted Adversarial Examples
- Towards Verified Artificial Intelligence
- Output Range Analysis for Deep Neural Networks
- DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
- Automated Verification of Neural Networks: Advances, Challenges and Perspectives
- Reachability Analysis of Deep Neural Networks with Provable Guarantees
- Verification of Binarized Neural Networks via Inter-Neuron Factoring
- nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems