Edge devices use neural network models learnt on cloud to predict labels of its data records, which may lead to incorrect predictions especially for records that are different from the data involved in the training process, i.e., out-of-distribution (OOD) records. However, recent efforts in OOD detection either require the retraining of the model or assume the existence of a certain amount of OOD records, thus limiting their application in practice. In this work, we propose a novel OOD detection method (named as NeuralFP) without requiring any access to OOD records, which constructs non-linear fingerprints of neural network models memorizing the information of data observed during training. The key idea of NeuralFP is to exploit the difference in how the neural network model responds to data records in its training set versus data records that are anomalous. Specifically, NeuralFP builds autoencoders for each layer of the neural network model and then carefully analyzes the error distribution of the autocoders in reconstructing the training set to identify OOD records. Through extensive experiments on multiple real-world datasets, we show the effectiveness of NeuralFP in detecting OOD records as well as its advantages over previous approaches. Furthermore, we provide useful guidelines for parameter selection in the practical adoption of NeuralFP.
In this paper, we present a novel incremental and decremental learning method for the least-squares support vector machine (LS-SVM). The goal is to adapt a pre-trained model to changes in the training dataset, without retraining the model on all the data, where the changes can include addition and deletion of data samples. We propose a provably exact method where the updated model is exactly the same as a model trained from scratch using the entire (updated) training dataset. Our proposed method only requires access to the updated data samples, the previous model parameters, and a unique, fixed-size matrix that quantifies the effect of the previous training dataset. Our approach can significantly reduce the storage requirement of model updating, preserve the privacy of unchanged training samples without loss of model accuracy, and enhance the computational efficiency. Experiments on real-world image dataset validate the effectiveness of our proposed method.
In this work, we develop a new data transformation technique to mediate privacy-preserving access to data while achieving machine learning (ML) tasks. Specifically, we first leverage mutual information in information theory to quantify the utility-providing information (corresponding to any ML task) and the privacy information (could be arbitrary information specified by the users). We further convert the optimization of utility-privacy tradeoff into training a novel neural network (named as NeuralTran) which consists of three modules: transformation module, utility module and privacy module. NeuralTran can be leveraged to automatically transform the input data to ensure that only utility-providing information is kept while the private information is removed. Through extensive experiments on real world datasets, we show the effectiveness of NeuralTran in balancing utility and privacy as well as its advantages over previous approaches.