Compositional Verification for Autonomous Systems with Deep Learning Components

@article{Pasareanu2018CompositionalVF,
  title={Compositional Verification for Autonomous Systems with Deep Learning Components},
  author={C. Pasareanu and D. Gopinath and H. Yu},
  journal={ArXiv},
  year={2018},
  volume={abs/1810.08303}
}
  • C. Pasareanu, D. Gopinath, H. Yu
  • Published 2018
  • Computer Science
  • ArXiv
  • As autonomy becomes prevalent in many applications, ranging from recommendation systems to fully autonomous vehicles, there is an increased need to provide safety guarantees for such systems. The problem is difficult, as these are large, complex systems which operate in uncertain environments, requiring data-driven machine-learning components. However, learning techniques such as Deep Neural Networks, widely used today, are inherently unpredictable and lack the theoretical foundations to… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 20 REFERENCES
    Compositional Falsification of Cyber-Physical Systems with Machine Learning Components
    • 96
    • PDF
    Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
    • 656
    • Highly Influential
    • PDF
    Stochastic Assume-Guarantee Contracts for Cyber-Physical System Design
    • 7
    • PDF
    Safety Verification of Deep Neural Networks
    • 417
    • PDF
    Verifying cyber-physical systems by combining software model checking with hybrid systems reachability
    • 5
    • PDF
    Assume-Guarantee Abstraction Refinement for Probabilistic Systems
    • 48
    • PDF
    Assume-Guarantee Abstraction Refinement Meets Hybrid Systems
    • 35
    • PDF
    Compositional assume-guarantee reasoning for input/output component theories
    • 20
    • PDF
    DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
    • 42
    • PDF