# Extracting Robust Register Automata from Neural Networks over Data Sequences

arXiv: https://arxiv.org/abs/2511.19100 · HTML: https://mlsanity.com/paper/2511.19100/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 83 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [Abduction-Based Explanations for Machine Learning Models](https://mlsanity.com/paper/1811.10656/) (2018)
- [Measuring Neural Net Robustness with Constraints](https://mlsanity.com/paper/1605.07262/) (2016)
- [Model Interpretability through the Lens of Computational Complexity](https://mlsanity.com/paper/2010.12265/) (2020)
- [Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples](https://mlsanity.com/paper/1711.09576/) (2017)
- [Instance-based Counterfactual Explanations for Time Series Classification](https://mlsanity.com/paper/2009.13211/) (2020)
- [On Explaining Decision Trees](https://mlsanity.com/paper/2010.11034/) (2020)
- [On Tackling Explanation Redundancy in Decision Trees](https://mlsanity.com/paper/2205.09971/) (2022)
- [SAT-Based Rigorous Explanations for Decision Lists](https://mlsanity.com/paper/2105.06782/) (2021)
- [Robustness of Neural Networks: A Probabilistic and Practical Approach](https://mlsanity.com/paper/1902.05983/) (2019)
- [On Efficiently Explaining Graph-Based Classifiers](https://mlsanity.com/paper/2106.01350/) (2021)
- [On Computing Probabilistic Explanations for Decision Trees](https://mlsanity.com/paper/2207.12213/) (2022)
- [Foundations of Symbolic Languages for Model Interpretability](https://mlsanity.com/paper/2110.02376/) (2021)
- [An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks](https://mlsanity.com/paper/1709.10380/) (2017)
- [Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces](https://mlsanity.com/paper/1904.02931/) (2019)
- [Extracting Finite Automata from RNNs Using State Merging](https://mlsanity.com/paper/2201.12451/) (2022)
- [Robustness Guarantees for Deep Neural Networks on Videos](https://mlsanity.com/paper/1907.00098/) (2019)
- [Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languages](https://mlsanity.com/paper/2206.14621/) (2022)
- [Automata theory in nominal sets](https://mlsanity.com/paper/1402.0897/) (2014)
- [Register automata with linear arithmetic](https://mlsanity.com/paper/1704.03972/) (2017)
- [Extracting Moore Machines from Transformers using Queries and Counterexamples](https://mlsanity.com/paper/2410.06045/) (2024)

## Built on by (most cited first, 1 of 1)

- [Synthesis and Verification of Transformer Programs (Technical Report)](https://mlsanity.com/paper/2602.16473/) (2026)

## Abstract (arXiv)

Automata extraction is a method for synthesising interpretable surrogates for black-box neural models that can be analysed symbolically. Existing techniques assume a finite input alphabet, and thus are not directly applicable to data sequences drawn from continuous domains. We address this challenge with deterministic register automata (DRAs), which extend finite automata with registers that store and compare numeric values. Our main contribution is a framework for robust DRA extraction from black-box models: we develop a polynomial-time robustness checker for DRAs with a fixed number of registers, and combine it with passive and active automata learning algorithms. This combination yields surrogate DRAs with statistical robustness and equivalence guarantees. As a key application, we use the extracted automata to assess the robustness of neural networks: for a given sequence and distance metric, the DRA either certifies local robustness or produces a concrete counterexample. Experiments on recurrent neural networks and transformer architectures show that our framework reliably learns accurate automata and enables principled robustness evaluation. Overall, our results demonstrate that robust DRA extraction effectively bridges neural network interpretability and formal reasoning without requiring white-box access to the underlying network.