Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems. CCS CONCEPTS• Software and its engineering → Software testing and debugging; • Theory of computation → Adversarial learning;
Deep learning (DL) defines a new data-driven programming paradigm where the internal system logic is largely shaped by the training data. The standard way of evaluating DL models is to examine their performance on a test dataset. The quality of the test dataset is of great importance to gain confidence of the trained models. Using an inadequate test dataset, DL models that have achieved high test accuracy may still lack generality and robustness. In traditional software testing, mutation testing is a well-established technique for quality evaluation of test suites, which analyzes to what extent a test suite detects the injected faults. However, due to the fundamental difference between traditional software and deep learning-based software, traditional mutation testing techniques cannot be directly applied to DL systems. In this paper, we propose a mutation testing framework specialized for DL systems to measure the quality of test data. To do this, by sharing the same spirit of mutation testing in traditional software, we first define a set of source-level mutation operators to inject faults to the source of DL (i.e., training data and training programs). Then we design a set of model-level mutation operators that directly inject faults into DL models without a training process. Eventually, the quality of test data could be evaluated from the analysis on to what extent the injected faults could be detected. The usefulness of the proposed mutation testing techniques is demonstrated on two public datasets, namely MNIST and CIFAR-10, with three DL models.
The single axis linear displacement measurement system of CMM is composed of grating ruler, servo motor and linear motion mechanism. Although the measuring accuracy of grating ruler is high, the accuracy of servo motor and linear motion mechanism is low. Therefore, the complex structure limits the measurement accuracy of the linear displacement measurement system. This paper introduces a novel linear displacement measurement system named magnetic levitation ruler. According to the working principle of grating ruler and the characteristics of magnetic levitation technology, the magnetic circuit design and structural design of magnetic levitation ruler are completed in this paper. The mover core of the magnetic levitation ruler is in the stable working magnetic field provided by the stator yoke. The horizontal control coil wound on the mover core can obtain more stable ampere force to improve the control accuracy of the mover core displacement. Therefore, the mover core can be moved in step mode, and the length of each step is fixed. Each step is the minimum scale of the magnetic levitation ruler. Therefore, the mover core can implement displacement measurement while moving in a linear motion. This paper analyzes the working principle of levitation, horizontal motion, and displacement measurement of magnetic levitation ruler, and determines the structural materials and parameters of magnetic levitation ruler with the help of finite element analysis software. The simulation results show that the levitation force of the magnetic levitation ruler is proportional to the current passing through the levitation coils, and the thrust of the horizontal control coil is less disturbed by the magnetic field. Compared with the linear displacement measurement system with rotational servo motor or permanent magnet synchronous linear motor as the core, the magnetic levitation ruler has stable magnetic field, strong controllability, high integration, and is easier to achieve high-precision control.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.