A New Perspective On AI Safety Through Control Theory Methodologies
Not on the map. Why?
Abstract (arXiv)
While artificial intelligence (AI) is advancing rapidly and mastering increasingly complex problems with astonishing performance, the safety assurance of such systems is a major concern. Particularly in the context of safety-critical, real-world cyber-physical systems, AI promises to achieve a new level of autonomy but is hampered by a lack of safety assurance. While data-driven control takes up recent developments in AI to improve control systems, control theory in general could be leveraged to improve AI safety. Therefore, this article outlines a new perspective on AI safety based on an interdisciplinary interpretation of the underlying data-generation process and the respective abstraction by AI systems in a system theory-inspired and system analysis-driven manner. In this context, the new perspective, also referred to as data control, aims to stimulate AI engineering to take advantage of existing safety analysis and assurance in an interdisciplinary way to drive the paradigm of data control. Following a top-down approach, a generic foundation for safety analysis and assurance is outlined at an abstract level that can be refined for specific AI systems and applications and is prepared for future innovation.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 104 of its 267 references that are in the map. First posted on arXiv 30 Jun 2025.
Builds on
104 of 267 references.
References · 104
- 2017Attention Is All You Needcited by 60,361
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
- 2015Fast R-CNNcited by 2,933
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
- 2016Concrete Problems in AI Safetycited by 1,642
38 more
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
- 2020Energy-based Out-of-distribution Detectioncited by 1,299
- 2019A Comprehensive Survey on Transfer Learningcited by 1,160
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
- 2021Domain Generalization: A Surveycited by 764
- 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
- 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
- 2018Disentangling by Factorisingcited by 616
- 2015Towards Open Set Deep Networkscited by 538
- 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 493
- 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
- 2018Conditional Neural Processescited by 426
- 2019Learning by Cheatingcited by 383
- 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
- 2017Stable Architectures for Deep Neural Networkscited by 341
- 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
- 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
- 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 291
- 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 289
- 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
- 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 270
- 2019Causality for Machine Learningcited by 243
- 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 240
- 2016Dense Associative Memory for Pattern Recognitioncited by 236
- 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
- 2018Neural Autoregressive Flowscited by 208
- 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
- 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
- 2023MotionLM: Multi-Agent Motion Forecasting as Language Modelingcited by 156
- 2022Model-Based Imitation Learning for Urban Drivingcited by 150
- 2020Neural Lyapunov Controlcited by 142
- 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 126
- 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 118
- 2022PlanT: Explainable Planning Transformers via Object-Level Representationscited by 105
- 2018Fast Decoding in Sequence Models using Discrete Latent Variablescited by 104
- 2019Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programmingcited by 101
- 2020Training robust neural networks using Lipschitz boundscited by 99
- 2018Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Searchcited by 82
50 most cited of 104 All 104 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.