Neural Networks for Runtime Verification

A recent trend in High-Performance Computation is parallel computing, and the field of Neural Networks is showing impressive improvements in performance, especially with the use of GPU accelerators. In this paper, we use neural networks to improve the performance of Runtime Verification. Runtime verification is used in a variety of domains -from policy enforcement to electronic fraud detection-to automatically check whether a system meets a temporal specification, by observing the output of the system. In this paper, we present a novel run-time monitoring system, RuleRunner, and we exploit results from the Neural-Symbolic Integration area to encode it in a recurrent neural network. The results show that neural networks can perform real-time online runtime verification. Performance was improved by the parallel architecture and the matrix-based implementation with GPU.

[1]  Nico Roos,et al.  Multiagent planning through plan repair , 2005, AAMAS '05.

[2]  Subbarao Kambhampati,et al.  Partial Satisfaction (Over-Subscription) Planning as Heuristic Search , 2004 .

[3]  Martin Leucker,et al.  Monitoring of Real-Time Properties , 2006, FSTTCS.

[4]  Martin Leucker,et al.  A brief account of runtime verification , 2009, J. Log. Algebraic Methods Program..

[5]  Jude W. Shavlik,et al.  Knowledge-Based Artificial Neural Networks , 1994, Artif. Intell..

[6]  Annie S. Wu,et al.  The Current State of Normative Agent-Based Systems , 2011, J. Artif. Soc. Soc. Simul..

[7]  Alan Perotti.  RuleRunner technical report , 2013, ArXiv.

[8]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Antonio Iera,et al.  The Internet of Things: A survey , 2010, Comput. Networks.

[10]  Martin Leucker,et al.  The Good, the Bad, and the Ugly, But How Ugly Is Ugly? , 2007, RV.

[11]  Paul Zikopoulos,et al.  Understanding Big Data: Analytics for Enterprise Class Hadoop and Streaming Data , 2011 .

[12]  Amir Pnueli,et al.  The Glory of the Past , 1985, Logic of Programs.

[13]  Yichuan Jiang,et al.  Cooperation among malicious agents: a general quantitative congestion game framework , 2012, AAMAS.

[14]  Tao Wang,et al.  Deep learning with COTS HPC systems , 2013, ICML.

[15]  Fred Kröger,et al.  Temporal Logic of Programs , 1987, EATCS Monographs on Theoretical Computer Science.

[16]  Steffen Hölldobler,et al.  Towards a New Massively Parallel Computational Model for Logic Programming , 1994 .

[17]  Howard Barringer,et al.  Rule Systems for Run-time Monitoring: from Eagle to RuleR , 2010, J. Log. Comput..

[18]  Artur S. d'Avila Garcez,et al.  The Connectionist Inductive Learning and Logic Programming System , 1999, Applied Intelligence.

[19]  Ricardo Seguel,et al.  Process Mining Manifesto , 2011, Business Process Management Workshops.

[20]  Roel Wieringa,et al.  Deontic logic in computer science: normative system specification , 1994 .

[21]  Janet Crawford,et al.  Evaluating the Outcomes of Plans: Theory, Practice, and Methodology , 2010 .

[22]  Dana Fisman,et al.  Reasoning with Temporal Logic on Truncated Paths , 2003, CAV.

[23]  Brian Charles Williams,et al.  Drake: An Efficient Executive for Temporal Plans with Choice , 2011, J. Artif. Intell. Res..