# Formal Verification of Long Short-Term Memory based Audio Classifiers: A Star based Approach

arXiv: https://arxiv.org/abs/2311.12130 · HTML: https://mlsanity.com/paper/2311.12130/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 20 of 20)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [SoundNet: Learning Sound Representations from Unlabeled Video](https://mlsanity.com/paper/1610.09001/) (2016)
- [Algorithms for Verifying Deep Neural Networks](https://mlsanity.com/paper/1903.06758/) (2019)
- [A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music](https://mlsanity.com/paper/1803.05428/) (2018)
- [NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems](https://mlsanity.com/paper/2004.05519/) (2020)
- [Convolutional Recurrent Neural Networks for Music Classification](https://mlsanity.com/paper/1609.04243/) (2016)
- [Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness](https://mlsanity.com/paper/1904.09959/) (2019)
- [ESResNet: Environmental Sound Classification Based on Visual Domain Models](https://mlsanity.com/paper/2004.07301/) (2020)
- [JuliaReach: a Toolbox for Set-Based Reachability](https://mlsanity.com/paper/1901.10736/) (2019)
- [Verifying Recurrent Neural Networks using Invariant Inference](https://mlsanity.com/paper/2004.02462/) (2020)
- [Formal Verification of CNN-based Perception Systems](https://mlsanity.com/paper/1811.11373/) (2018)
- [Convolutional Neural Network Achieves Human-level Accuracy in Music Genre Classification](https://mlsanity.com/paper/1802.09697/) (2018)
- [A Tool for Neural Network Global Robustness Certification and Training](https://mlsanity.com/paper/2208.07289/) (2022)
- [Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the L0 Norm](https://mlsanity.com/paper/1804.05805/) (2018)
- [A Neurosymbolic Approach to the Verification of Temporal Logic Properties of Learning enabled Control Systems](https://mlsanity.com/paper/2303.05394/) (2023)
- [Robustness Verification of Deep Neural Networks using Star-Based Reachability Analysis with Variable-Length Time Series Input](https://mlsanity.com/paper/2307.13907/) (2023)
- [Improving the Environmental Perception of Autonomous Vehicles using Deep Learning-based Audio Classification](https://mlsanity.com/paper/2209.04075/) (2022)

## Abstract (arXiv)

Formally verifying audio classification systems is essential to ensure accurate signal classification across real-world applications like surveillance, automotive voice commands, and multimedia content management, preventing potential errors with serious consequences. Drawing from recent research, this study advances the utilization of star-set-based formal verification, extended through reachability analysis, tailored explicitly for Long Short-Term Memory architectures and their Convolutional variations within the audio classification domain. By conceptualizing the classification process as a sequence of set operations, the star set-based reachability approach streamlines the exploration of potential operational states attainable by the system. The paper serves as an encompassing case study, validating and verifying sequence audio classification analytics within real-world contexts. It accentuates the necessity for robustness verification to ensure precise and dependable predictions, particularly in light of the impact of noise on the accuracy of output classifications.