Robust Spectral Filtering and Anomaly Detection Machine Learning

We consider a setting, where the output of a linear dynamical system (LDS) is, with an unknown but fixed probability, replaced by noise. There, we present a robust method for the prediction of the outputs of the LDS and identification of the samples of noise, and prove guarantees on its statistical performance. One application lies in anomaly detection: the samples of noise, unlikely to have been generated by the dynamics, can be flagged to operators of the system for further study.

Compact Surjective Encoding Autoencoder for Unsupervised Novelty Detection Machine Learning

In unsupervised novelty detection, a model is trained solely on the in-class data, and infer to single out out-class data. Autoencoder (AE) variants aim to compactly model the in-class data to reconstruct it exclusively, differentiating it from out-class by the reconstruction error. However, imposing compactness improperly may damage in-class reconstruction and, therefore, detection performance. To solve this, we propose Compact Surjective Encoding AE (CSE-AE). In this model, the encoding of any input is constrained into a compact manifold by exploiting the deep neural net's ignorance of the unknown. Concurrently, the in-class data is surjectively encoded to the compact manifold via AE. The mechanism is realized by both GAN and its ensembled discriminative layers, and results to reconstruct the in-class exclusively. In inference, the reconstruction error of a query is measured using high-level semantics captured by the discriminator. Extensive experiments on image data show that the proposed model gives state-of-the-art performance.

Learning to Detect Machine Learning

In this paper we consider Multiple-Input-Multiple-Output (MIMO) detection using deep neural networks. We introduce two different deep architectures: a standard fully connected multi-layer network, and a Detection Network (DetNet) which is specifically designed for the task. The structure of DetNet is obtained by unfolding the iterations of a projected gradient descent algorithm into a network. We compare the accuracy and runtime complexity of the purposed approaches and achieve state-of-the-art performance while maintaining low computational requirements. Furthermore, we manage to train a single network to detect over an entire distribution of channels. Finally, we consider detection with soft outputs and show that the networks can easily be modified to produce soft decisions.

Abnormal Client Behavior Detection in Federated Learning Machine Learning

In federated learning systems, clients are autonomous in that their behaviors are not fully governed by the server. Consequently, a client may intentionally or unintentionally deviate from the prescribed course of federated model training, resulting in abnormal behaviors, such as turning into a malicious attacker or a malfunctioning client. Timely detecting those anomalous clients is therefore critical to minimize their adverse impacts. In this work, we propose to detect anomalous clients at the server side. In particular, we generate low-dimensional surrogates of model weight vectors and use them to perform anomaly detection. We evaluate our solution through experiments on image classification model training over the FEMNIST dataset. Experimental results show that the proposed detection-based approach significantly outperforms the conventional defense-based methods.

CNN Architectures for Large-Scale Audio Classification Machine Learning

Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with 30,871 video-level labels. We examine fully connected Deep Neural Networks (DNNs), AlexNet [1], VGG [2], Inception [3], and ResNet [4]. We investigate varying the size of both training set and label vocabulary, finding that analogs of the CNNs used in image classification do well on our audio classification task, and larger training and label sets help up to a point. A model using embeddings from these classifiers does much better than raw features on the Audio Set [5] Acoustic Event Detection (AED) classification task.