As the machine learning-related technology has made great progress in recent years, deep neural networks are widely used in many scenarios, including security-critical ones, which may incura great loss when DNN is compromised. Starting from introducing several commonly used bit-flip methods, this paper concentrates on bit-flips attacks aiming DNN and the corresponding defense methods. We analyze the threat models, methods design, and effect of attack and defense methods in detail, drawing some helpful conclusions about improving the robustness and resilience of DNN. In addition, we point out several drawbacks to existing works, which can hopefully be researched in the future.

One of the key challenges for question answering is to bridge the lexical gap between questions and answers because there may not be any matching word between them. Machine translation models have been shown to boost the performance of solving the lexical gap problem between question-answer pairs. In this paper, we introduce an attention-based deep learning model to address the answer selection task for question answering. The proposed model employs a bidirectional long short-term memory (LSTM) encoder-decoder, which has been demonstrated to be effective on machine translation tasks to bridge the lexical gap between questions and answers. Our model also uses a step attention mechanism which allows the question to focus on a certain part of the candidate answer. Finally, we evaluate our model using a benchmark dataset and the results show that our approach outperforms the existing approaches. Integrating our model significantly improves the performance of our question answering system in the TREC 2015 LiveQA task.

To address the issue of insufficient testing caused by the continuous reduction of software development cycles, many organizations maintain bug repositories and bug tracking systems to ensure real-time updates of bugs. However, each day, a large number of bugs is discovered and sent to the repository, which imposes a heavy workload on bug fixers. Therefore, effective bug deduplication and triage are of great significance in software development. This paper provides a comprehensive investigation and survey of the recent developments in bug deduplication and triage. The study begins by outlining the roadmap of the existing literature, including the research trends, mathematical models, methods, and commonly used datasets in recent years. Subsequently, the paper summarizes the general process of the methods from two perspectives—runtime information-based and bug report-based perspectives—and provides a detailed overview of the methodologies employed in relevant works. Finally, this paper presents a detailed comparison of the experimental results of various works in terms of usage methods, datasets, accuracy, recall rate, and F1 score. Drawing on key findings, such as the need to improve the accuracy of runtime information collection and refine the description information in bug reports, we propose several potential future research directions in the field, such as stack trace enrichment and the combination of new NLP models.

An elliptical Hough transform (EHT) algorithm is proposed in the framework of track-before-detect (TBD) for joint detection and tracking of weak exoatmospheric targets. The new approach exploits the fact that when restricted to a two-body problem, the exoatmospheric target often follows an elliptical orbit, and thus the Hough transform integrated with orbital geometry information would have better detection performance. The relationship between the original radar measurements in data space and the elliptical parameters in parameter space is explicitly derived with multiple steps of coordinate transformation. It is found that the data points mapping into the parameter space essentially represent a quartic curve. An EHT-based algorithm is then designed, and orbit planarity is also taken into account to reduce the effect of noise accumulation. The influences of primary and secondary thresholds and the signal-to-noise ratio (SNR) on the detection performance are compared by simulations. Additionally, a real radar tracking dataset from a scientific satellite on 28 May 2017 is used to investigate the efficiency of the method. By adding some imaginary clutter to the raw orbit, the results indicate that it is very effective in detecting the real satellite trajectory in a low signal-to-noise ratio (SNR) environment. The advantage of the new method lies in it can not only simultaneously detect and track weak exoatmospheric targets but also can predict the trajectory by using these available detected parameters.

Community Question Answering(CQA) services become popular recently. In most existing CQA service, the question posted by real user is usually consist by two parts: question title and body. And there is a semantic relation between them. It is necessary to analyze the relation between title and body. In this paper, we propose a deep neural network based method to analyze and quantify the relation between question title and body. The proposed method employs Bidirectional LSTM to read the title and body separately. And finally our model outputs a relevance score to measure the semantic relation between the question title and body. We evaluate our model on the Yahoo!Answers dataset and the experimental results show our method is effective.