# FlexFringe: Modeling Software Behavior by Learning Probabilistic Automata

arXiv: https://arxiv.org/abs/2203.16331 · HTML: https://mlsanity.com/paper/2203.16331/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 116 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 6 of 6)

- [Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples](https://mlsanity.com/paper/1711.09576/) (2017)
- [Interpretable Sequence Classification via Discrete Optimization](https://mlsanity.com/paper/2010.02819/) (2020)
- [Explaining Black Boxes on Sequential Data using Weighted Automata](https://mlsanity.com/paper/1810.05741/) (2018)
- [Interpreting Finite Automata for Sequential Data](https://mlsanity.com/paper/1611.07100/) (2016)
- [Timed k-Tail: Automatic Inference of Timed Automata](https://mlsanity.com/paper/1705.08399/) (2017)
- [PRINS: Scalable Model Inference for Component-based System Logs](https://mlsanity.com/paper/2106.01987/) (2021)

## Built on by (most cited first, 2 of 2)

- [Extending AALpy with Passive Learning: A Generalized State-Merging Approach](https://mlsanity.com/paper/2506.06333/) (2025)
- [Robust Attack Graph Generation](https://mlsanity.com/paper/2206.07776/) (2022)

## Abstract (arXiv)

We present the efficient implementations of probabilistic deterministic finite automaton learning methods available in FlexFringe. These implement well-known strategies for state-merging including several modifications to improve their performance in practice. We show experimentally that these algorithms obtain competitive results and significant improvements over a default implementation. We also demonstrate how to use FlexFringe to learn interpretable models from software logs and use these for anomaly detection. Although less interpretable, we show that learning smaller more convoluted models improves the performance of FlexFringe on anomaly detection, outperforming an existing solution based on neural nets.