arXiv subjects

Jie Shi

Publications and source records attributed to Jie Shi.

62 records · Page 4Linked to original sources

arXiv2021

Rethinking Natural Adversarial Examples for Classification Models

Recently, it was found that many real-world examples without intentional modifications can fool machine learning models, and such examples are called "natural adversarial examples". ImageNet-A is a famous dataset of natural adversarial examples. By analyzing this dataset, we hypothesized that large, cluttered and/or unusual background is an important reason why the images in this dataset are difficult to be classified. We validated the hypothesis by reducing the background influence in ImageNet-A examples with object detection techniques. Experiments showed that the object detection models with various classification models as backbones obtained much higher accuracy than their corresponding classification models. A detection model based on the classification model EfficientNet-B7 achieved a top-1 accuracy of 53.95%, surpassing previous state-of-the-art classification models trained on ImageNet, suggesting that accurate localization information can significantly boost the performance of classification models on ImageNet-A. We then manually cropped the objects in images from ImageNet-A and created a new dataset, named ImageNet-A-Plus. A human test on the new dataset showed that the deep learning-based classifiers still performed quite poorly compared with humans. Therefore, the new dataset can be used to study the robustness of classification models to the internal variance of objects without considering the background disturbance.

cs.CV↗

arXiv2020

Where Does the Robustness Come from? A Study of the Transformation-based Ensemble Defence

This paper aims to provide a thorough study on the effectiveness of the transformation-based ensemble defence for image classification and its reasons. It has been empirically shown that they can enhance the robustness against evasion attacks, while there is little analysis on the reasons. In particular, it is not clear whether the robustness improvement is a result of transformation or ensemble. In this paper, we design two adaptive attacks to better evaluate the transformation-based ensemble defence. We conduct experiments to show that 1) the transferability of adversarial examples exists among the models trained on data records after different reversible transformations; 2) the robustness gained through transformation-based ensemble is limited; 3) this limited robustness is mainly from the irreversible transformations rather than the ensemble of a number of models; and 4) blindly increasing the number of sub-models in a transformation-based ensemble does not bring extra robustness gain.

cs.LG↗

arXiv2020

Batch-Constrained Reinforcement Learning for Dynamic Distribution Network Reconfiguration

Dynamic distribution network reconfiguration (DNR) algorithms perform hourly status changes of remotely controllable switches to improve distribution system performance. The problem is typically solved by physical model-based control algorithms, which not only rely on accurate network parameters but also lack scalability. To address these limitations, this paper develops a data-driven batch-constrained reinforcement learning (RL) algorithm for the dynamic DNR problem. The proposed RL algorithm learns the network reconfiguration control policy from a finite historical operational dataset without interacting with the distribution network. The numerical study results on three distribution networks show that the proposed algorithm not only outperforms state-of-the-art RL algorithms but also improves the behavior control policy, which generated the historical operational data. The proposed algorithm is also very scalable and can find a desirable network reconfiguration solution in real-time.

eess.SY↗

arXiv2020

Deep Quaternion Features for Privacy Protection

We propose a method to revise the neural network to construct the quaternion-valued neural network (QNN), in order to prevent intermediate-layer features from leaking input information. The QNN uses quaternion-valued features, where each element is a quaternion. The QNN hides input information into a random phase of quaternion-valued features. Even if attackers have obtained network parameters and intermediate-layer features, they cannot extract input information without knowing the target phase. In this way, the QNN can effectively protect the input privacy. Besides, the output accuracy of QNNs only degrades mildly compared to traditional neural networks, and the computational cost is much less than other privacy-preserving methods.

cs.LG↗

arXiv2020

Rotation-Equivariant Neural Networks for Privacy Protection

In order to prevent leaking input information from intermediate-layer features, this paper proposes a method to revise the traditional neural network into the rotation-equivariant neural network (RENN). Compared to the traditional neural network, the RENN uses d-ary vectors/tensors as features, in which each element is a d-ary number. These d-ary features can be rotated (analogous to the rotation of a d-dimensional vector) with a random angle as the encryption process. Input information is hidden in this target phase of d-ary features for attribute obfuscation. Even if attackers have obtained network parameters and intermediate-layer features, they cannot extract input information without knowing the target phase. Hence, the input privacy can be effectively protected by the RENN. Besides, the output accuracy of RENNs only degrades mildly compared to traditional neural networks, and the computational cost is significantly less than the homomorphic encryption.

cs.LG↗

arXiv2019

Information Losses in Neural Classifiers from Sampling

This paper considers the subject of information losses arising from the finite datasets used in the training of neural classifiers. It proves a relationship between such losses as the product of the expected total variation of the estimated neural model with the information about the feature space contained in the hidden representation of that model. It then bounds this expected total variation as a function of the size of randomly sampled datasets in a fairly general setting, and without bringing in any additional dependence on model complexity. It ultimately obtains bounds on information losses that are less sensitive to input compression and in general much smaller than existing bounds. The paper then uses these bounds to explain some recent experimental findings of information compression in neural networks which cannot be explained by previous work. Finally, the paper shows that not only are these bounds much smaller than existing ones, but that they also correspond well with experiments.

cs.LG↗

arXiv2019

Smart Building Energy Management using Nonlinear Economic Model Predictive Control

Owing to the call for energy efficiency, the need to optimize the energy consumption of commercial buildings-- responsible for over 40% of US energy consumption--has recently gained significant attention. Moreover, the ability to participate in the retail electricity markets through proactive demand-side participation has recently led to development of economic model predictive control (EMPC) for building's Heating, Ventilation, and Air Conditioning (HVAC) system. The objective of this paper is to develop a price-sensitive operational model for building's HVAC systems while considering inflexible loads and other distributed energy resources (DERs) such as photovoltaic (PV) generation and battery storage for the buildings. A Nonlinear Economic Model Predictive Controller (NL-EMPC) is presented to minimize the net cost of energy usage by building's HVAC system while satisfying the comfort-level of building's occupants. The efficiency of the proposed NL-EMPC controller is evaluated using several simulation case studies.

eess.SY↗

arXiv2014

Quantification and visualization of variation in anatomical trees

This paper presents two approaches to quantifying and visualizing variation in datasets of trees. The first approach localizes subtrees in which significant population differences are found through hypothesis testing and sparse classifiers on subtree features. The second approach visualizes the global metric structure of datasets through low-distortion embedding into hyperbolic planes in the style of multidimensional scaling. A case study is made on a dataset of airway trees in relation to Chronic Obstructive Pulmonary Disease.

stat.AP↗