Towards the Verification of Neural Networks for Critical Cyber-Physical Systems

@inproceedings{Rabatin2018TowardsTV,
  title={Towards the Verification of Neural Networks for Critical Cyber-Physical Systems},
  author={G{\'a}bor Rabatin and Andr{\'a}s V{\"o}r{\"o}s},
  year={2018}
}
Smart technologies are emerging in the field of Cyber-Physical Systems (CPS) yielding new challenges for system engineers. Rigorous techniques are necessitated to ensure the correct and accident-free behaviour of critical CPS. Neural networks gain increasing popularity in CPS, and even critical functionalities may rely on neural network based solutions. In this paper, we overview the literature and summarize our experiences of a neural network verification algorithm used in an academic case… CONTINUE READING

Figures and Tables from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 29 REFERENCES

DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars

  • 2018 IEEE/ACM 40th International Conference on Software Engineering (ICSE)
  • 2017
VIEW 1 EXCERPT