DeepSafe: a data-driven approach for assessing robustness of neural networks
From MaRDI portal
Recommendations
- Safety verification of deep neural networks
- A game-based approximate verification of deep neural networks with provable guarantees
- Probabilistic robustness estimates for feed-forward neural networks
- Enhancing robustness verification for deep neural networks via symbolic propagation
- Reluplex: a calculus for reasoning about deep neural networks
Cited in
(16)- A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability
- Improving neural network verification through spurious region guided refinement
- Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training
- Safety verification of deep neural networks
- An SMT-based approach for verifying binarized neural networks
- A game-based approximate verification of deep neural networks with provable guarantees
- Theorem Proving in Higher Order Logics
- Metrics and methods for robustness evaluation of neural networks with generative models
- Reluplex: a calculus for reasoning about deep neural networks
- Boosting robustness verification of semantic feature neighborhoods
- Verifying generalization in deep learning
- Robustness verification of support vector machines
- Verifying the generalization of deep learning to out-of-distribution domains
- Minimal modifications of deep neural networks using verification
- DiffRNN: differential verification of recurrent neural networks
- Robustness verification of semantic segmentation neural networks using relaxed reachability
This page was built for publication: DeepSafe: a data-driven approach for assessing robustness of neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6109575)
