mlsanityData to 7 Oct 2026

Towards Verified Artificial Intelligence

arXiv 1606.08514 ↗First posted 27 Jun 2016cs.AIcited by 36

Not on the map. Why?

Abstract (arXiv)

Verified artificial intelligence (AI) is the goal of designing AI-based systems that that have strong, ideally provable, assurances of correctness with respect to mathematically-specified requirements. This paper considers Verified AI from a formal methods perspective. We describe five challenges for achieving Verified AI, and five corresponding principles for addressing these challenges.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 10; 2023: 8; 2024: 3; 2025: 1; 2026: 5.

36 papers.

Sort:

By area:

  1. 2021Trustworthy AI: From Principles to Practicescited by 206
  2. 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 94
  3. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  4. 2021Software Engineering for AI-Based Systems: A Surveycited by 68
  5. 2022Logic-Based Explainability in Machine Learningcited by 47
  6. 2021Categorical Foundations of Gradient-Based Learningcited by 44
  7. 2023Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attackcited by 37
  8. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  9. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
  10. 2023From Robustness to Explainability and Back Againcited by 14
  11. 2023Disproving XAI Myths with Formal Methods -- Initial Resultscited by 12
  12. 2022If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Componentscited by 11
24 more
  1. 2022Correct-by-Construction Runtime Enforcement in AI -- A Surveycited by 10
  2. 2021A Review of Testing Object-Based Environment Perception for Safe Automated Drivingcited by 9
  3. 2023Design Principles for Lifelong Learning AI Acceleratorscited by 9
  4. 2021Parallel and Multi-Objective Falsification with Scenic and VerifAIcited by 8
  5. 2022PAC Verification of Statistical Algorithmscited by 8
  6. 2021Customizable Reference Runtime Monitoring of Neural Networks using Resolution Boxescited by 6
  7. 2022Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identificationcited by 6
  8. 2023What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systemscited by 6
  9. 2025Space Explanations of Neural Network Classificationcited by 5
  10. 2026Skilldex: A Package Manager and Registry for Agent Skill Packages with Hierarchical Scope-Based Distributioncited by 5
  11. 2021Weighted Graph-Based Signal Temporal Logic Inference Using Neural Networkscited by 4
  12. 2023Robustness Verification for Knowledge-Based Logic of Risky Driving Scenescited by 3
  13. 2024Deep Learning with Parametric Lensescited by 3
  14. 2022Test and Evaluation of Quadrupedal Walking Gaits through Sim2Real Gap Quantificationcited by 1
  15. 2022Understanding the Impact of Edge Cases from Occluded Pedestrians for ML Systemscited by 1
  16. 2023Safety of autonomous vehicles: A survey on Model-based vs. AI-based approachescited by 1
  17. 2026Learning Contextual Runtime Monitors for Safe AI-Based Autonomycited by 1
  18. 2026Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systemscited by 1
  19. 2021Certifiable Artificial Intelligence Through Data Fusioncited by 0
  20. 2022Safe AI -- How is this Possible?cited by 0
  21. 2022An Empirical Analysis of the Use of Real-Time Reachability for the Safety Assurance of Autonomous Vehiclescited by 0
  22. 2024Probabilistic ML Verification via Weighted Model Integrationcited by 0
  23. 2026Interactions Between Crosscoder Features: A Compact Proofs Perspectivecited by 0
  24. 2026Neuron Activation-based Computation of Logical Explanations for Deep Neural Networkscited by 0