Formal Verification of Long Short-Term Memory based Audio Classifiers: A Star based Approach
This work addresses the need for reliable audio classifiers in critical domains like surveillance and automotive systems, though it is incremental as it extends existing formal verification methods to specific neural network architectures.
The paper tackles the problem of ensuring accurate audio classification in real-world applications by formally verifying Long Short-Term Memory (LSTM) and Convolutional LSTM architectures using a star-set-based reachability analysis approach, demonstrating its effectiveness in validating robustness against noise.
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.