Corpus ID: 53249794

DeepSaucer: Unified Environment for Verifying Deep Neural Networks

@article{Sato2018DeepSaucerUE,
  title={DeepSaucer: Unified Environment for Verifying Deep Neural Networks},
  author={Naoto Sato and Hironobu Kuruma and M. Kaneko and Y. Nakagawa and H. Ogawa and T. Hoang and Michael J. Butler},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.03752}
}
In recent years, a number of methods for verifying DNNs have been developed. Because the approaches of the methods differ and have their own limitations, we think that a number of verification methods should be applied to a developed DNN. To apply a number of methods to the DNN, it is necessary to translate either the implementation of the DNN or the verification method so that one runs in the same environment as the other. Since those translations are time-consuming, a utility tool, named… Expand

References

SHOWING 1-10 OF 12 REFERENCES
Testing Deep Neural Networks
  • 104
  • PDF
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
  • 792
  • PDF
Validating a deep learning framework by metamorphic testing
  • 12
Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
  • 258
  • PDF
Identifying implementation bugs in machine learning based image classifiers using metamorphic testing
  • 61
  • PDF
DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
  • 54
  • PDF
Safety Verification of Deep Neural Networks
  • 504
  • PDF
DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars
  • 500
  • PDF
Metamorphic Testing
  • 144
  • PDF
Fault-based testing in the absence of an oracle
  • 37
  • PDF
...
1
2
...