mlsanityData to 7 Oct 2026

Safe AI -- How is this Possible?

arXiv 2201.10436 ↗First posted 25 Jan 2022cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Ttraditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems which are acting in largely unpredictable operating contexts. We outline some of underlying challenges of safe AI and suggest a rigorous engineering framework for minimizing uncertainty, thereby increasing confidence, up to tolerable levels, in the safe behavior of AI systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 49 of its 130 references that are in the map. First posted on arXiv 25 Jan 2022.

Builds on

49 of 130 references.

References · 49

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  3. 2016Concrete Problems in AI Safetycited by 1,582
  4. 2016End to End Learning for Self-Driving Carscited by 1,000
  5. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  6. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  7. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  8. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  9. 2017One pixel attack for fooling deep neural networkscited by 579
  10. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  11. 2016Safety Verification of Deep Neural Networkscited by 262
  12. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
37 more
  1. 2020Logical Neural Networkscited by 118
  2. 2017Maximum Resilience of Artificial Neural Networkscited by 97
  3. 2018Reachability Analysis of Deep Neural Networks with Provable Guaranteescited by 93
  4. 2017Verifying Properties of Binarized Deep Neural Networkscited by 77
  5. 2018TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzingcited by 67
  6. 2018Concolic Testing for Deep Neural Networkscited by 51
  7. 2021Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)cited by 40
  8. 2016Towards Verified Artificial Intelligencecited by 36
  9. 2018Testing Deep Neural Networkscited by 36
  10. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
  11. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  12. 2018Runtime Monitoring Neuron Activation Patternscited by 34
  13. 2017Output Range Analysis for Deep Neural Networkscited by 30
  14. 2018SOTER: A Runtime Assurance Framework for Programming Safe Robotics Systemscited by 24
  15. 2018Verification for Machine Learning, Autonomy, and Neural Networks Surveycited by 24
  16. 2019Epistemic Uncertainty Samplingcited by 24
  17. 2018Semantic Adversarial Deep Learningcited by 15
  18. 2018Towards Dependability Metrics for Neural Networkscited by 13
  19. 2018Using Machine Learning Safely in Automotive Software: An Assessment and Adaption of Software Process Requirements in ISO 26262cited by 13
  20. 2018Quantitative Projection Coverage for Testing ML-enabled Autonomous Systemscited by 11
  21. 2019Autonomous Vehicles Meet the Physical World: RSS, Variability, Uncertainty, and Proving Safety (Expanded Version)cited by 10
  22. 2018DeepRoad: GAN-based Metamorphic Autonomous Driving System Testingcited by 9
  23. 2019Perpetual Assurances for Self-Adaptive Systemscited by 9
  24. 2019Towards Safety Verification of Direct Perception Neural Networkscited by 9
  25. 2018Symbolic Execution for Deep Neural Networkscited by 8
  26. 2019A Formalization of Robustness for Deep Neural Networkscited by 8
  27. 2018Compositional Verification for Autonomous Systems with Deep Learning Componentscited by 6
  28. 2020Assurance 2.0: A Manifestocited by 6
  29. 2017A Component-Based Simplex Architecture for High-Assurance Cyber-Physical Systemscited by 5
  30. 2021Risk-Based Safety Envelopes for Autonomous Vehicles Under Perception Uncertaintycited by 4
  31. 2016A comprehensive safety engineering approach for software-intensive systems based on STPAcited by 3
  32. 2021SaDe: Learning Models that Provably Satisfy Domain Constraintscited by 3
  33. 2019A Symbolic Neural Network Representation and its Application to Understanding, Verifying, and Patching Networkscited by 2
  34. 2020Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learningcited by 2
  35. 2016Structural Synthesis for GXW Specificationscited by 1
  36. 2020Advancing the Scientific Frontier with Increasingly Autonomous Systemscited by 1
  37. 2020Application of the Neural Network Dependability Kit in Real-World Environmentscited by 1

Built on by

Not cited yet.