NeVer: a tool for artificial neural networks verification

The adoption of Artificial Neural Networks (ANNs) in safety-related applications is often avoided because it is difficult to rule out possible misbehaviors with traditional analytical or probabilistic techniques. In this paper we present NeVer, our tool for checking safety of ANNs. NeVer encodes the problem of verifying safety of ANNs into the problem of satisfying corresponding Boolean combinations of linear arithmetic constraints. We describe the main verification algorithm and the structure of NeVer. We present also empirical results confirming the effectiveness of NeVer on realistic case studies.

[1]  Inês Lynce,et al.  Conflict-Driven Clause Learning SAT Solvers , 2009, Handbook of Satisfiability.

[2]  Thomas Schubert,et al.  High-level formal verification of next-generation microprocessors , 2003, Proceedings 2003. Design Automation Conference (IEEE Cat. No.03CH37451).

[3]  Ian Witten,et al.  Data Mining , 2000 .

[4]  Jim Austin,et al.  Developing artificial neural networks for safety critical systems , 2006, Neural Computing and Applications.

[5]  Eran Yahav,et al.  Abstraction-guided synthesis of synchronization , 2010, POPL.

[6]  Patrick Cousot,et al.  Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints , 1977, POPL.

[7]  Helmut Veith,et al.  Counterexample-guided abstraction refinement for symbolic model checking , 2003, JACM.

[8]  Toby Walsh,et al.  Handbook of satisfiability , 2009 .

[9]  Joseph Sifakis,et al.  Specification and verification of concurrent systems in CESAR , 1982, Symposium on Programming.

[10]  Toby Walsh,et al.  Handbook of Constraint Programming , 2006, Handbook of Constraint Programming.

[11]  Ingo Mierswa,et al.  YALE: rapid prototyping for complex data mining tasks , 2006, KDD '06.

[12]  Sriram K. Rajamani,et al.  SLAM and Static Driver Verifier: Technology Transfer of Formal Methods inside Microsoft , 2004, IFM.

[13]  Stephan Merz,et al.  Model Checking , 2000 .

[14]  Alan K. Mackworth.  Consistency in Networks of Relations , 1977, Artif. Intell..

[15]  Diana F. Gordon,et al.  Asimovian Adaptive Agents , 2000, J. Artif. Intell. Res..

[16]  Johann Schumann,et al.  On Verification & Validation of Neural Network Based Controllers , 2003 .

[17]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[18]  Luca Pulina,et al.  An Abstraction-Refinement Approach to Verification of Artificial Neural Networks , 2010, CAV.

[19]  Kenneth Gl Simpson,et al.  Functional Safety: A Straightforward Guide to Applying IEC 61508 and Related Standards , 2004 .

[20]  Alessandro Armando,et al.  LTL model checking for security protocols , 2009, J. Appl. Non Class. Logics.

[21]  I-Cheng Yeh,et al.  Modeling of strength of high-performance concrete using artificial neural networks , 1998 .

[22]  Armando Solar-Lezama,et al.  Sketching concurrent data structures , 2008, PLDI '08.

[23]  Pascal Van Hentenryck,et al.  Numerica: A Modeling Language for Global Optimization , 1997, IJCAI.

[24]  Jin-Kao Hao,et al.  A Population and Interval Constraint Propagation Algorithm , 2003, EMO.

[25]  Thomas A. Henzinger,et al.  Automatic symbolic verification of embedded systems , 1993, 1993 Proceedings Real-Time Systems Symposium.

[26]  Cesare Tinelli,et al.  Satisfiability Modulo Theories , 2021, Handbook of Satisfiability.

[27]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[28]  Martin Fränzle,et al.  Efficient Solving of Large Non-linear Arithmetic Constraint Systems with Complex Boolean Structure , 2007, J. Satisf. Boolean Model. Comput..

[29]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .