an active learning approach to the falsification of black
play

An Active Learning Approach to the Falsification of Black Box - PowerPoint PPT Presentation

Oct 21, 2023 •326 likes •692 views

An Active Learning Approach to the Falsification of Black Box Cyber-Physical Systems Simone Silvetti , Alberto Policriti, Luca Bortolussi silvetti.simone@spes.uniud.it silvetti@esteco.com 13th International Conference on integrated Formal

  1. An Active Learning Approach to the Falsification of Black Box Cyber-Physical Systems Simone Silvetti , Alberto Policriti, Luca Bortolussi silvetti.simone@spes.uniud.it silvetti@esteco.com 13th International Conference on integrated Formal Methods S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 1 / 35

  2. Outline Overview 1 Model Based Development Signal Temporal Logic Search-Based Testing Domain Estimation Problem 2 Algorithm Idea Test Case & Results 3 Challenges & Further studies 4 S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 2 / 35

  3. Overview Model Based Development Overview Model Based Development Methodology based on a computational model of a real target system used at the early stage of the design phase used at the end to verify the compliance of the real system Motivations reducing the time of prototyping reducing the cost of development S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 3 / 35

  4. Overview Model Based Development Models Software: Block Diagram Systems Computational Models LabView Hybrid Systems CPS Automata Statistical Models Simulink Problem Too Much Complexity ⇒ no stan- dard Model checking techniques. Solution Black Box Assumption and Search-based approach . S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 4 / 35

  5. Overview Model Based Development Simulink Model S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 5 / 35

  6. Overview Model Based Development Simulink Model - Inputs S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 6 / 35

  7. Overview Model Based Development Simulink Model - Outputs S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 7 / 35

  8. Overview Model Based Development Simulink Model - Continuous Dynamics S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 8 / 35

  9. Overview Model Based Development Simulink Model - Finite State Machine S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 9 / 35

  10. Overview Model Based Development Black Box Assumption Inputs & Outputs The Inputs are Piece Wise Constant (PWC) Functions, the Outputs are PWC functions (Gear) or Continuous Functions. S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 10 / 35

  11. Overview Model Based Development Black Box Assumption Black Box Assumption less information an more general approach (interesting by an industrial point of view) S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 11 / 35

  12. Overview Signal Temporal Logic The requirements: Signal Temporal Logic (STL) Signal temporal logic is: a linear continuous time temporal logic. X ) ≥ 0 ] where g : R n → R is a continuous the atomic predicates are of the form µ ( � X ):=[ g ( � function. the syntax is φ := ⊥ | ⊤ | µ | ¬ φ | φ ∨ φ | φ U [ T 1 , T 2 ] φ, (1) Example φ 1 := F [ 0 , 50 ] | X 1 − X 2 | > 10 The Booleans semantics: if a given path 1 satisfies or not a given STL formula. The Quantitative semantics: How much a 2 given path satisfies or not a given STL formula. S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 12 / 35

  13. Overview Search-Based Testing Search-Based Testing Falsification Goal: Find the input functions (1) which violate the requirements (4) Problems 1 Falsify with a low number of simulations ⇒ Active Learning 2 Functional Input Space(!!) ⇒ Adaptive Space Parameterization S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 13 / 35

  14. Overview Search-Based Testing Fixed Parameterization n adaptive control points ⇒ n variable to optimize S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 14 / 35

  15. Overview Search-Based Testing Fixed Parameterization n fixed control points ⇒ n variable to optimize S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 15 / 35

  16. Overview Search-Based Testing Adaptive Parameterization n adaptive control points ⇒ 2n variable to optimize S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 16 / 35

  17. Domain Estimation Problem Domain Estimation Problem Domain Estimation Problem Consider a function ρ : Θ → R and an interval I ⊆ R . We define the domain estimation problem as the task of identifying the set: B = { θ ∈ Θ | f ( θ ) ∈ I } ⊆ Θ (2) In practice, if B � = ∅ , we will limit us to identify a subset B ⊆ B of size n. Falsification ∼ Domain estimation problems B = { θ ∈ Θ | ρ ( θ ) ∈ ( −∞ , 0 ) } ⊆ Θ Gaussian Processes S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 17 / 35

  18. Domain Estimation Problem Gaussian Processes Definition A random variable f ( θ ) , θ ∈ Θ is a GP f ∼ GP ( m , k ) ⇐ ⇒ ( f ( θ 1 ) , f ( θ 2 ) , . . . , f ( θ n )) ∼ N ( m , K ) where m = ( m ( θ 1 ; h 1 ) , m ( θ 2 ; h 1 ) , . . . , m ( θ n ; h 1 )) and K ij = k ( f ( θ i ) , f ( θ j ); h 2 ) Prediction { f ( θ 1 ) , . . . , f ( θ n ) , f ( θ ′ ) } ∼ N ( m ′ , K ′ ) E ( f ( θ ′ )) = ( k ( θ ′ , θ 1 ) , . . . , k ( θ ′ , θ N )) K − 1 r N var ( f ( θ ′ )) = k ( θ ′ , θ ′ ) − K ( θ, r ) K − 1 K ( θ, r ) T N S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 18 / 35

  19. Domain Estimation Problem Algorithm Idea Domain Estimation Problem Domain Estimation Problem Train Set: K ( ρ ) = { ( θ i , ρ ( θ i ) ) } i ≤ n (the partial knowledge) Gaussian Process: ρ K ( θ ) ∼ GP ( m K ( θ ) , σ K ( θ )) (the partial model) � 0 − m K ( θ ) � P ( ρ K ( θ ) < 0 ) = CDF σ K ( θ ) Simple Idea Iteratively explore the area which is more probable to falsify the system by sampling from P ( ρ K ( θ ) < 0 ) . S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 19 / 35

  20. Domain Estimation Problem Algorithm Idea Algorithm - I S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 20 / 35

  21. Domain Estimation Problem Algorithm Idea Algorithm - II S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 21 / 35

  22. Domain Estimation Problem Algorithm Idea Aglorithm - III S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 22 / 35

  23. Domain Estimation Problem Algorithm Idea Algorithm - IV S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 23 / 35

  24. Domain Estimation Problem Algorithm Idea Algorithm - V S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 24 / 35

  25. Domain Estimation Problem Algorithm Idea Algorithm - VI S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 25 / 35

  26. Domain Estimation Problem Algorithm Idea Algorithm - VII S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 26 / 35

  27. Domain Estimation Problem Algorithm Idea Algorithm - VIII S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 27 / 35

  28. Domain Estimation Problem Algorithm Idea Algorithm - IX S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 28 / 35

  29. Domain Estimation Problem Algorithm Idea Algorithm - X S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 29 / 35

  30. Domain Estimation Problem Algorithm Idea Algorithm - XI S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 30 / 35

  31. Domain Estimation Problem Algorithm Idea Probabilistic Approximation Semantics Definition ( L 0 and L ) L 0 : [ ⊂ STL]: atomic propositions + φ 1 U T φ 2 , F T φ, G T φ , that cannot be equivalently written as Boolean combinations of simpler formulas; F T ( φ 1 ∨ φ 2 ) ≡ F T φ 1 ∨ F T φ 2 �∈ L 0 L : the boolean connective closure of L 0 . Definition (Probabilistic Approximation Semantics of L ) The probabilistic approximation function γ : L × Path M × [ 0 , ∞ ) → [ 0 , 1 ] is defined by: γ ( φ, θ, t ) = P ( f K ( φ ) ( θ ) > 0 ) γ ( ¬ ψ, θ, t ) = 1 − γ ( ψ, θ, t ) γ ( ψ 1 ∧ ψ 2 , θ, t ) = γ ( ψ 1 , θ, t ) ∗ γ ( ψ 2 , θ, t ) γ ( ψ 1 ∨ ψ 2 , θ, t ) = γ ( ψ 1 , θ, t ) + γ ( ψ 2 , θ, t ) − γ ( ψ 1 ∧ ψ 2 , θ, t ) S. Silvetti , A. Policriti, L. Bortolussi iFM 2017 September 20, 2017 31 / 35

Recommend

Andy Reed OBE Saje Impact Sports Think Tank The Black Box Approach - Learning from Failure,

Andy Reed OBE Saje Impact Sports Think Tank The Black Box Approach - Learning from Failure,

Andy Reed OBE Saje Impact Sports Think Tank The Black Box Approach - Learning from Failure, knowing what works and why! The Problem If our aim is to get the Nation Physically Active we are Failing. Like most sectors we are afraid to admit

461 views • 26 slides
Hybrid System Falsification and Reinforcement Learning Formal Method for Cyber-Physical Systems

Hybrid System Falsification and Reinforcement Learning Formal Method for Cyber-Physical Systems

Hybrid System Falsification and Reinforcement Learning Formal Method for Cyber-Physical Systems Clovis Eberhart David Sprunger National Institute of Technology, Japan SOKENDAI lesson, July 1, 8, and 22 1 / 31 Quick reminder Falsification:

405 views • 36 slides
Active Learning Passive Learning Active Learning 1. Think 1. Acquisition of knowledge Ability

Active Learning Passive Learning Active Learning 1. Think 1. Acquisition of knowledge Ability

Active Learning Passive Learning Active Learning 1. Think 1. Acquisition of knowledge Ability 2. Decision making 2. Application of knowledge 3. Explain/communicate 1. Deep learning Approach to Uni-directional 2. Interactive Learning

282 views • 5 slides
Information, Learning and Falsification David Balduzzi December 17, 2011 Max Planck Institute

Information, Learning and Falsification David Balduzzi December 17, 2011 Max Planck Institute

Effective information Algorithmic information Learning theory Falsification Conclusion Information, Learning and Falsification David Balduzzi December 17, 2011 Max Planck Institute for Intelligent Systems T ubingen, Germany Effective

695 views • 43 slides
Teachnology: Learning About Learning Through an Active, Authentic Approach to Using Technology

Teachnology: Learning About Learning Through an Active, Authentic Approach to Using Technology

Teachnology: Learning About Learning Through an Active, Authentic Approach to Using Technology Christy Raymond Assistant Professor Margot Zemrau - Graduate Student Jose Benito Tovillo - Graduate Student Jessica Ley - Instructional

296 views • 13 slides
Agenda Intro to Active Learning Activity Design Resources for Active Learning Lunch with Active

Agenda Intro to Active Learning Activity Design Resources for Active Learning Lunch with Active

Agenda Intro to Active Learning Activity Design Resources for Active Learning Lunch with Active Learning Veterans Wrap Up Introduction to Active Learning What is active learning? Brainstorm your ideas with your group and generate a

855 views • 42 slides
Multi-Task Active Learning Yi Zhang Outline Active Learning Multi-Task Active Learning

Multi-Task Active Learning Yi Zhang Outline Active Learning Multi-Task Active Learning

Multi-Task Active Learning Yi Zhang Outline Active Learning Multi-Task Active Learning Linguistic Annotations (ACL 08) Image Classification (CVPR 08) Current Work and Discussions Constraint-Driven Active Learning

945 views • 47 slides
Just Sort It! A Simple and E ff ective Approach to Active Preference Learning Lucas Maystre,

Just Sort It! A Simple and E ff ective Approach to Active Preference Learning Lucas Maystre,

Just Sort It! A Simple and E ff ective Approach to Active Preference Learning Lucas Maystre, Matthias Grossglauser School of Computer and Communication Sciences, EPFL ICML August 8 th , 2017 Goal Learning a ranking from noisy pairwise

299 views • 17 slides
Hybrid System Falsification and Reinforcement Learning Formal Method for Cyber-Physical Systems

Hybrid System Falsification and Reinforcement Learning Formal Method for Cyber-Physical Systems

Hybrid System Falsification and Reinforcement Learning Formal Method for Cyber-Physical Systems Clovis Eberhart David Sprunger National Institute of Technology, Japan SOKENDAI lesson, July 1, 8, and 22 1 / 50 Lecture structure Lectures

1.01k views • 83 slides
ACTIVE 1. WELCOME and JUMPING IN LEARNING 1. WHAT IS ACTIVE LEARNING? la Carte 1.

ACTIVE 1. WELCOME and JUMPING IN LEARNING 1. WHAT IS ACTIVE LEARNING? la Carte 1.

ACTIVE 1. WELCOME and JUMPING IN LEARNING 1. WHAT IS ACTIVE LEARNING? la Carte 1. CONSTRUCTING our TEACHING CHALLENGES in a low tech 1. ORCHESTRATION environment 1. SHOW-AND-TELL Selma Hamdani Psychology / DALC / Neuroscience

836 views • 50 slides
An Active Learning Approach to STEM Writing Intensive Courses Dr. Corey Ptak Director of

An Active Learning Approach to STEM Writing Intensive Courses Dr. Corey Ptak Director of

An Active Learning Approach to STEM Writing Intensive Courses Dr. Corey Ptak Director of Integrated Academic Support Programs The Learning Center Rutgers The State University of New Jersey Writing in STEM classes Learning to Writing to

353 views • 18 slides
Census of Active Super Massive Black Holes Active Super Massive Black Holes in the Era of

Census of Active Super Massive Black Holes Active Super Massive Black Holes in the Era of

Census of Active Super Massive Black Holes Active Super Massive Black Holes in the Era of Violent Growth Masayuki Akiyama (Tohoku Univ ) Masayuki Akiyama (Tohoku Univ.) () 2013/01/27 Hokkaido University Black

544 views • 43 slides
Adaptive Submodularity: A New Approach to Active Learning and Stochastic Optimization Daniel

Adaptive Submodularity: A New Approach to Active Learning and Stochastic Optimization Daniel

Adaptive Submodularity: A New Approach to Active Learning and Stochastic Optimization Daniel Golovin and Andreas Krause (FYI, a powerpoint version of these slides is available on Daniel Golovins website.) 1 Max K-Cover (Oil Spill Edition) 2

299 views • 19 slides
12.1 Active Learning: A Review When learning, it may be the case that getting the true labels of

12.1 Active Learning: A Review When learning, it may be the case that getting the true labels of

CS/CNS/EE 253: Advanced Topics in Machine Learning Topic: Active Learning Review and Kernel Methods Lecturer: Andreas Krause Scribe: Jonathan Krause Date: Feb. 17, 2010 12.1 Active Learning: A Review When learning, it may be the case that getting

213 views • 5 slides
Predator and Prey: Active Learning Is Social Learning Kenneth Ronkowitz Active Learning

Predator and Prey: Active Learning Is Social Learning Kenneth Ronkowitz Active Learning

Predator and Prey: Active Learning Is Social Learning Kenneth Ronkowitz Active Learning Symposium, Rutgers University, May 15, 2018 Typically part of the curriculum in biology, phrenology, biology, anatomy, craniometry, physiognomy, crime

484 views • 14 slides
Learning Loss for Active Learning Rymarczyk D., Zieliski B., Tabor J., Sadowski M., Titov M.

Learning Loss for Active Learning Rymarczyk D., Zieliski B., Tabor J., Sadowski M., Titov M.

Learning Loss for Active Learning Rymarczyk D., Zieliski B., Tabor J., Sadowski M., Titov M. Agenda 1. Active Learning introduction 2. Base methods in AL for Deep Learning 3. Learning Loss for Active Learning 4. Our ideas for Active

802 views • 43 slides
10.1 Active Learning Review What questions should be asked in order to collect best data?

10.1 Active Learning Review What questions should be asked in order to collect best data?

CS/CNS/EE 253: Advanced Topics in Machine Learning Topic: Active Learning 2: the myopic version-space shrinking strategy Lecturer: Daniel Golovin Scribe: Pete Trautman Date: 8 February 2010 10.1 Active Learning Review What questions should be

264 views • 4 slides
Active Learning: Rethinking Our Teaching to Promote Deeper Learning Facilitated by Ken Silvestri,

Active Learning: Rethinking Our Teaching to Promote Deeper Learning Facilitated by Ken Silvestri,

Active Learning: Rethinking Our Teaching to Promote Deeper Learning Facilitated by Ken Silvestri, CFE Instructional Designer Adapted for Institute of Technology By Menaka Abraham OVERVIEW Why Active Learning What is Active Learning

542 views • 18 slides
Active Learning for Regression: Active Learning for Regression: Algorithms and Applications

Active Learning for Regression: Active Learning for Regression: Algorithms and Applications

LAMDA group, Nanjing University Nov. 5, 2009. Active Learning for Regression: Active Learning for Regression: Algorithms and Applications Algorithms and Applications Masashi Sugiyama Tokyo Institute of Technology sugi@cs.titech.ac.jp

870 views • 64 slides
Classroom-Tested Strategies for Overcoming Student Resistance to Active Learning Connect your

Classroom-Tested Strategies for Overcoming Student Resistance to Active Learning Connect your

Classroom-Tested Strategies for Overcoming Student Resistance to Active Learning Connect your approach to what learners value Gary Smith Director, Office for Medical Educator Development Professor, Organization, Information, &amp; Learning

409 views • 37 slides
Learning how to Active Learn: A Deep Reinforcement Learning Approach Meng Fang, Yuan Li, Trevor

Learning how to Active Learn: A Deep Reinforcement Learning Approach Meng Fang, Yuan Li, Trevor

Learning how to Active Learn: A Deep Reinforcement Learning Approach Meng Fang, Yuan Li, Trevor Cohn The University of Melbourne Presenter: Jialin Song April 05, 2018 April 05, 2018 1 / 17 Meng Fang, Yuan Li, Trevor Cohn CS 546 Machine

708 views • 55 slides
Using active learning pedagogy to enable the Presentation by Donna Whitehead teaching of

Using active learning pedagogy to enable the Presentation by Donna Whitehead teaching of

Using active learning pedagogy to enable the Presentation by Donna Whitehead teaching of enterprise and entrepreneurial skills Active learning Active learning methodology has become a preferred way to change the traditional teacher

146 views • 11 slides
Using R for Active Learning and Self-assessment in an e-Learning Environment Arnau Mir, Margaret

Using R for Active Learning and Self-assessment in an e-Learning Environment Arnau Mir, Margaret

Using R for Active Learning and Self-assessment in an e-Learning Environment Arnau Mir, Margaret Mir-Juli and Monica J. Ruiz-Mir University of the Balearic Islands Palma de Mallorca, SPAIN Using R for Active Learning and Self-assessment

740 views • 12 slides
Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo

Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo

Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo Institute of Technology Active Learning (NLP Motivation) NLP (common scenario) Large amounts of unlabeled data Large amounts of unlabeled

706 views • 36 slides

More recommend