As the core component of aero engines, compressor blades in turbine engines have complex surface geometry requirements. With the rapid iteration of the turbine power system, the compressor blades used are constantly updated. An accurate prediction model that can quickly adapt to new blade production on manufacturing processes is urgently needed. However, most of the existing technologies cannot meet the high precision requirements of blade manufacturing, and the lack of data for newer blades makes training a predictive model in a new machining task a high time and economic cost. In this paper, we propose a domain generalization-based quality prediction framework for high-precision compressor blade manufacturing processes. The framework can make full use of the relevant manufacturing process data of historical blades to build a domain generalization model for adapting to the prediction of processing accuracy of new blades that have not been processed before. In particular, this study proposes a non-invasive generalization solution that meets accuracy requirements. Coordinate measuring machine (CMM) data is used as input features for prediction, rather than retrofitting sensors onto machinery after installation. To evaluate the effectiveness of the proposed framework, experiments were conducted on four series of aerospace compressor blades from Wuxi Turbine Blade Co., Ltd., China. CMM data from key stages such as blade root milling and integrated precision milling are used as input to predict final geometric errors. Comparison results verify that the proposed framework achieves the smallest prediction error at 0.037 mm, 0.013 mm, 0.021 mm, and 0.016 mm for four blades respectively.

Deep learning techniques have achieved promising results in code clone detection in the past decade. However, existing techniques merely focus on how to extract more dis-criminative features from source codes, while some issues, such as structural differences of functional similar codes, are not explicitly addressed. This phenomenon is common when programmers copy a code segment along with adding or removing several statements, or use a more flexible syntax structure to implement the same function. In this paper, we unify the aforementioned problems as the problem of code misalignment, and propose a novel code alignment network to tackle it. We design a bi-directional causal convolutional neural network to extract feature representations of code fragments with rich structural and semantical information. After feature extraction, our method learns to align the two code fragments in a data-driven fashion. We present two independent strategies for code alignment, namely attention-based alignment and sparse reconstruction-based alignment. Both two strategies strive to learn an alignment matrix that represents the correspondences between two code fragments. Our method outperforms state-of-the-art methods in terms of F1 score by 0.5% and 3.1 % on BigCloneBench and OJClone, respectively11Our code is available at https://github.com/ArcticHare105/Code-Alignment.

Existing researches have recently shown that adversarial stylometry of source code can confuse source code authorship identification (SCAI) models, which may threaten the security of related applications such as programmer attribution, software forensics, etc. In this work, we propose source code authorship disguise (SCAD) to automatically hide programmers' identities from authorship identification, which is more practical than the previous work that requires to known the output probabilities or internal details of the target SCAI model. Specifically, SCAD trains a substitute model and develops a set of semantically equivalent transformations, based on which the original code is modified towards a disguised style with small manipulations in lexical features and syntactic features. When evaluated under totally black-box settings, on a real-world dataset consisting of 1,600 programmers, SCAD induces state-of-the-art SCAI models to cause above 30% misclassification rates. The efficiency and utility-preserving properties of SCAD are also demonstrated with multiple metrics. Furthermore, our work can serve as a guideline for developing more robust identification methods in the future.

The development of deep learning techniques has significantly increased the ability of computers to recognize CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart), thus breaking or mitigating the security of existing captcha schemes. To protect against these attacks, recent works have been proposed to leverage adversarial machine learning to perturb captcha pictures. However, they either require the prior knowledge of captcha solving models or lack adaptivity to the evolving behaviors of attackers. Most importantly, none of them has been deployed in practical applications, and their practical applicability and effectiveness are unknown.

In this paper, we study the privacy of online health data. We present a novel online health data De-Anonymization (DA) framework, named De-Health. Leveraging two real world online health datasets WebMD and HealthBoards, we validate the DA efficacy of De-Health. We also present a linkage attack framework which can link online health/medical information to real world people. Through a proof-of-concept attack, we link 347 out of 2805 WebMD users to real world people, and find the full names, medical/health information, birthdates, phone numbers, and other sensitive information for most of the re-identified users. This clearly illustrates the fragility of the privacy of those who use online health forums.

Maintaining service availability during an inter-domain route update is a challenge in both conventional networks and software-defined networks (SDNs). In the update process, asynchronous reconfigurations to border forwarding devices in different domains will incur transient anomalies with numerous packet losses and service disruptions. Based on current SDN inter-domain routing mechanisms, we in this paper propose a lossless and seamless method for SDN inter-domain route updates. This method is lightweight, and it has no requirement to add extra switch functionality or to extend SDN southbound protocols. The primary idea of this method is to achieve a lossless inter-domain route update by communications and collaborations among relevant domains. Motivated by this idea, we first identify three different domain categories for the update, i.e., domains only on the new inter-domain route, domains on both the old and new inter-domain routes, and domains only on the old inter-domain route. We further find that the transient anomalies are able to be avoided by reconfiguring the related border switches of the three categories of domains in order. Four update steps are then designed to keep the orderly update. Furthermore, we present the theoretical proof of the effectiveness of this method. Finally, based on our prototype implementation, the proposed method is also validated by simulation studies, and the simulation results indicate that this method succeeds in avoiding packet loss and maintaining service availability during the update.