Sora: Scalable black-box reachability analyser on neural networks
The vulnerability of deep neural networks (DNNs) to input perturbations has posed a
significant challenge. Recent work on robustness verification of DNNs not only lacks …
significant challenge. Recent work on robustness verification of DNNs not only lacks …
Model-agnostic reachability analysis on deep neural networks
Verification plays an essential role in the formal analysis of safety-critical systems. Most
current verification methods have specific requirements when working on Deep Neural …
current verification methods have specific requirements when working on Deep Neural …
[PDF][PDF] Data-driven assessment of deep neural networks with random input uncertainty
BG Anderson, S Sojoudi - arXiv preprint arXiv …, 2020 - people.eecs.berkeley.edu
When using deep neural networks to operate safety-critical systems, assessing the
sensitivity of the network outputs when subject to uncertain inputs is of paramount …
sensitivity of the network outputs when subject to uncertain inputs is of paramount …
Reachability analysis of deep neural networks with provable guarantees
Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic
reachability problem for feed-forward DNNs which, for a given set of inputs to the network …
reachability problem for feed-forward DNNs which, for a given set of inputs to the network …
Star-based reachability analysis of deep neural networks
This paper proposes novel reachability algorithms for both exact (sound and complete) and
over-approximation (sound) analysis of deep neural networks (DNNs). The approach uses …
over-approximation (sound) analysis of deep neural networks (DNNs). The approach uses …
Reachnn*: A tool for reachability analysis of neural-network controlled systems
We introduce ReachNN*, a tool for reachability analysis of neural-network controlled
systems (NNCSs). The theoretical foundation of ReachNN* is the use of Bernstein …
systems (NNCSs). The theoretical foundation of ReachNN* is the use of Bernstein …
Polar-express: Efficient and precise formal reachability analysis of neural-network controlled systems
Neural networks (NNs) playing the role of controllers have demonstrated impressive
empirical performance on challenging control problems. However, the potential adoption of …
empirical performance on challenging control problems. However, the potential adoption of …
Robustness verification of swish neural networks embedded in autonomous driving systems
With the applications of deep learning in safety-critical domains such as autonomous driving
systems gaining ground, it demands rigorous verification to guarantee the safety and …
systems gaining ground, it demands rigorous verification to guarantee the safety and …
Enhancing robustness verification for deep neural networks via symbolic propagation
Deep neural networks (DNNs) have been shown lack of robustness, as they are vulnerable
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …
Verification of recurrent neural networks for cognitive tasks via reachability analysis
Abstract Recurrent Neural Networks (RNNs) are one of the most successful neural network
architectures that deal with temporal sequences, eg, speech and text recognition. Recently …
architectures that deal with temporal sequences, eg, speech and text recognition. Recently …