skip to main content
10.1145/3302504.3313351acmconferencesArticle/Chapter ViewAbstractPublication PagescpsweekConference Proceedingsconference-collections
demonstration
Public Access

Sherlock - A tool for verification of neural network feedback systems: demo abstract

Published: 16 April 2019 Publication History

Abstract

We present an approach for the synthesis and verification of neural network controllers for closed loop dynamical systems, modelled as an ordinary differential equation. Feedforward neural networks are ubiquitous when it comes to approximating functions, especially in the machine learning literature. The proposed verification technique tries to construct an over-approximation of the system trajectories using a combination of tools, such as, Sherlock and Flow*. In addition to computing reach sets, we incorporate counter examples or bad traces into the synthesis phase of the controller as well. We go back and forth between verification and counter example generation until the system outputs a fully verified controller, or the training fails to terminate in a neural network which is compliant with the desired specifications. We demonstrate the effectiveness of our approach over a suite of benchmarks ranging from 2 to 17 variables.

References

[1]
X. Chen, E. Ábrahám, and S. Sankaranarayanan. 2013. Flow*: An Analyzer for Non-linear Hybrid Systems. In Proc. of CAV'13 (LNCS), Vol. 8044. Springer, 258--263.
[2]
Souradeep Dutta, Susmit Jha, Sriram Sankaranarayanan, and Ashish Tiwari. {n. d.}. Output Range Analysis for Deep Feedforward Neural Networks. NFM 2018 (to appear), Cf. https://arxiv.org/pdf/1709.09130.pdf.
[3]
Souradeep Dutta, Susmit Jha, Sriram Sankaranarayanan, and Ashish Tiwari. 2018. Learning and Verification of Feedback Control Systems using Feedforward Neural Networks. IFAC-PapersOnLine 51, 16 (2018), 151 -- 156. 6th IFAC Conference on Analysis and Design of Hybrid Systems ADHS 2018.
[4]
Rüdiger Ehlers. 2017. Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks. In ATVA (Lecture Notes in Computer Science), Vol. 10482. Springer, 269--286.
[5]
Guy Katz, Clark Barrett, David L. Dill, Kyle Julian, and Mykel J. Kochenderfer. 2017. Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks. Springer International Publishing, Cham, 97--117.

Cited By

View all

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
HSCC '19: Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control
April 2019
299 pages
ISBN:9781450362825
DOI:10.1145/3302504
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 16 April 2019

Check for updates

Author Tags

  1. flowpipe construction
  2. hybrid system
  3. neural network
  4. polynomial regression
  5. reachability analysis

Qualifiers

  • Demonstration

Funding Sources

  • US NSF
  • US ARL Cooperative Agreement

Conference

HSCC '19
Sponsor:

Acceptance Rates

Overall Acceptance Rate 153 of 373 submissions, 41%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)81
  • Downloads (Last 6 weeks)12
Reflects downloads up to 02 Feb 2025

Other Metrics

Citations

Cited By

View all

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media