Certifying Neural Network Audio Classifiers

25 Sep 2019  ·  Wonryong Ryou, Mislav Balunovic, Gagandeep Singh, Martin Vechev ·

We present the first end-to-end verifier of audio classifiers. Compared to existing methods, our approach enables analysis of both, the entire audio processing stage as well as recurrent neural network architectures (e.g., LSTM). The audio processing is verified using novel convex relaxations tailored to feature extraction operations used in audio (e.g., Fast Fourier Transform) while recurrent architectures are certified via a novel binary relaxation for the recurrent unit update. We show the verifier scales to large networks while computing significantly tighter bounds than existing methods for common audio classification benchmarks: on the challenging Google Speech Commands dataset we certify 95% more inputs than the interval approximation (only prior scalable method), for a perturbation of -90dB.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here