Robustness Guarantees for Deep Neural Networks on Videos

@article{Wu2020RobustnessGF,
  title={Robustness Guarantees for Deep Neural Networks on Videos},
  author={M. Wu and M. Kwiatkowska},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={308-317}
}
  • M. Wu, M. Kwiatkowska
  • Published 2020
  • Computer Science, Engineering
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
The widespread adoption of deep learning models places demands on their robustness. [...] Key Method We demonstrate that, under the assumption of Lipschitz continuity, the problem can be approximated using finite optimisation via discretising the optical flow space, and the approximation has provable guarantees.Expand
8 Citations
Safety and Robustness for Deep Learning with Provable Guarantees
  • M. Kwiatkowska
  • Computer Science
  • 2020 35th IEEE/ACM International Conference on Automated Software Engineering (ASE)
  • 2020
  • PDF
Fast Falsification of Neural Networks using Property Directed Testing
  • PDF
Performance Evaluation of Various ANN Architectures Using Proposed Cost Function
  • Sandhya, Udayan Ghose, Upasana Bisht
  • Computer Science
  • 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)
  • 2020
  • 1
  • Highly Influenced
Software Architecture for ML-based Systems: What Exists and What Lies Ahead
  • PDF
Assessing Robustness of Text Classification through Maximal Safe Radius Computation
  • 1
  • PDF
Efficient Certification of Spatial Robustness
  • 2
  • PDF
Fast and Effective Robustness Certification for Recurrent Neural Networks
  • 2
  • PDF

References

SHOWING 1-10 OF 46 REFERENCES
Sparse Adversarial Perturbations for Videos
  • 37
  • PDF
Safety Verification of Deep Neural Networks
  • 522
  • PDF
Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid
  • 58
  • PDF
The Limitations of Deep Learning in Adversarial Settings
  • 2,025
  • PDF
DeepSafe: A Data-Driven Approach for Assessing Robustness of Neural Networks
  • 40
  • PDF
Universal Adversarial Perturbations
  • 1,178
  • PDF
Output Range Analysis for Deep Feedforward Neural Networks
  • 131
  • PDF
Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
  • 171
  • PDF
...
1
2
3
4
5
...