Certifying Neural Network Audio Classifiers
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio ClassificationSimilar Papers 제목 키워드 기반
Self-Certifying Classification by Linearized Deep Assignment
We propose a novel class of deep stochastic predictors for classifying metric data on graphs within the PAC-Bayes risk certification paradigm. Classifiers are realized as linearly parametrized deep assignment flows with …
ClassificationCertifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data au…
Adversarial RobustnessData AugmentationCertifying Ensembles: A General Certification Theory with S-Lipschitzness
Improving and guaranteeing the robustness of deep learning models has been a topic of intense research. Ensembling, which combines several classifiers to provide a better model, has shown to be beneficial for generalisat…
Listenable Maps for Zero-Shot Audio Classifiers
Interpreting the decisions of deep learning models, including audio classifiers, is crucial for ensuring the transparency and trustworthiness of this technology. In this paper, we introduce LMAC-ZS (Listenable Maps for A…
Decoderzero-shot-classificationZero-Shot LearningImproving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers
Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical robustness. In principle, convex relaxat…