检索结果-内蒙古大学图书馆

Robin: A novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Zhen Zhang, Ruqian Zou, Deqing Wang, Ning Li, Yating Xu, Shouhuai Chen, Chen Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Colorado Colorado Springs United States Center for Research in Computer Vision University of Central Florida United States School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier;the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

Runtime Permission Issues in Android Apps: Taxonomy, Practices, and Ways Forward

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Ying Wang, Yibo Wang, Sinan Liu, Yepang Xu, Chang Cheung, Shing-Chi Yu, Hai Zhu, Zhiliang The Software College Northeasthern University China The Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China The State Key Lab for Novel Software Technology The Department of Computer Science and Technology Nanjing University China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong

Android introduces a new permission model that allows apps to request permissions at runtime rather than at the installation time since 6.0 (Marshmallow, API level 23). While this runtime permission model provides users with greater flexibility in controlling an app’s access to sensitive data and system features, it brings new challenges to app development. First, as users may grant or revoke permissions at any time while they are using an app, developers need to ensure that the app properly checks and requests required permissions before invoking any permission-protected APIs. Second, Android’s permission mechanism keeps evolving and getting customized by device manufacturers. Developers are expected to comprehensively test their apps on different Android versions and device models to make sure permissions are properly requested in all situations. Unfortunately, these requirements are often impractical for developers. In practice, many Android apps suffer from various runtime permission issues (ARP issues). While existing studies have explored ARP issues, the understanding of such issues is still preliminary. To better characterize ARP issues, we performed an empirical study using 135 Stack Overflow posts that discuss ARP issues and 199 real ARP issues archived in popular open-source Android projects on GitHub. Via analyzing the data, we observed 11 types of ARP issues that commonly occur in Android apps. For each type of issues, we systematically studied: (1) how they can be manifested, (2) how pervasive and serious they are in real-world apps, and (3) how they can be fixed. We also analyzed the evolution trend of different types of issues from 2015 to 2020 to understand their impact on the Android ecosystem. Furthermore, we conducted a field survey and in-depth interviews among practitioners, to gain insights from industrial practices and learn practitioners’ requirements of tools that can help combat ARP issues. Finally, to understand the strengths and weaknesse

关键词： Android (operating system)

Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liang, Hanzhe Xie, Guoyang Hou, Chengbin Wang, Bingshu Gao, Can Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Audencia Financial Technology Institute Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Intelligent Manufacturing CATL Ningde China School of Computing and Artificial Intelligence Fuyao University of Science and Technology Fuzhou China School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Zhuo Zhu, Miaoxi Xia, Xiaobo Shen, Li Yu, Jun Gong, Chen Han, Bo Du, Bo Liu, Tongliang Syndey Ai Centre The University of Sydney Australia National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Jd Explore Academy China Department of Automation University of Science and Technology of China China Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science Hong Kong Baptist University Hong Kong

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains. Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization

Physics-informed Inverse Design of Multi-bit Programmable Metasurfaces

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Yucheng Yang, Jia-Qi Fan, Kebin Wang, Sheng Wu, Jingbo Zhang, Caihong Zhan, De-Chuan Padilla, Willie J. Jin, Biaobing Chen, Jian Wu, Peiheng Key Laboratory of Optoelectronic Devices and Systems with Extreme Performances of MOE School of Electronic Science and Engineering Nanjing University Nanjing210023 China Purple Mountain Laboratories Nanjing211111 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Department of Electrical and Computer Engineering Duke University Box 90291 DurhamNC27708 United States

Emerging reconfigurable metasurfaces offer various possibilities in programmatically manipulating electromagnetic waves across spatial, spectral, and temporal domains, showcasing great potential for enhancing terahertz applications. However, they are hindered by limited tunability, particularly evident in relatively small phase tuning over 270o, due to the design constraints with time-intensive forward design methodologies. Here, we demonstrate a multi-bit programmable metasurface capable of terahertz beam steering, facilitated by a developed physics-informed inverse design (PIID) approach. Through integrating a modified coupled mode theory (MCMT) into residual neural networks, our PIID algorithm not only significantly increases the design accuracy compared to conventional neural networks but also elucidates the intricate physical relations between the geometry and the modes. Without decreasing the reflection intensity, our method achieves the enhanced phase tuning as large as 300o. Additionally, we experimentally validate the inverse designed programmable beam steering metasurface, which is adaptable across 1-bit, 2-bit, and tri-state coding schemes, yielding a deflection angle up to 68o and broadened steering coverage. Our demonstration provides a promising pathway for rapidly exploring advanced metasurface devices, with potentially great impact on communication and imaging technologies. © 2024, CC0.

关键词： Tuning

TSGN: Transaction Subgraph Networks Assisting Phishing Detection in Ethereum

学校读者我要写书评

暂无评论

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Wang, Jinhuan Chen, Pengtao Xu, Xinyao Wu, Jiajing Shen, Meng Xuan, Qi Yang, Xiaoniu Zhejiang University of Technology Institute of Cyberspace Security College of Information Engineering Hangzhou310023 China ZJUT Binjiang Institute of Artificial Intelligence Hangzhou310056 China Fudan University Adaptive Networks and Control Lab Department of Electronic Engineering School of Information Science and Technology Shanghai200433 China Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Shenzhen518066 China National Key Laboratory of Electromagnetic Space Security Jiaxing314033 China

Due to the decentralized and public nature of the blockchain ecosystem, malicious activities on the Ethereum platform impose immeasurable losses on users. At the same time, the transparency of cryptocurrency transactions provides a unique opportunity to analyze illegal activities, such as phishing scams, from a network perspective. Most existing phishing scam detection methods focus primarily on analyzing account interaction networks, which limits their ability to uncover transaction behavior patterns embedded within transaction interactions. To address this, we construct the Transaction SubGraph Network (TSGN) by using transaction subgraphs as basic elements and further propose a novel framework for Ethereum phishing account detection. Specifically, we rebuild the graph structures via three well-designed mapping mechanisms, yielding TSGN and its two variants, i.e., Directed-TSGN and Temporal-TSGN, to obtain direction-aware and time-aware transfer flow features. By further incorporating the mapping strategy into transaction multidigraphs, we develop the Multiple-TSGN, which could preserve more transaction flow features while concurrently reducing the time consumption of modeling large-scale networks. TSGN models based on transaction subgraph interactions can capture complex higher-order dependencies, which lay beyond the reach of models that exclusively capture pairwise account interactions. As a general framework, our model can incorporate various feature extraction methods to improve the performance of phishing detection. Extensive experimental results on Ethereum datasets show that our method achieves superior performance in phishing detection, yielding 3.27%∼6.71% relative improvement over previous state-of-the-art. © 2004-2012 IEEE.

关键词： Phishing

Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shi, Guangchen Wu, Yirui Liu, Jun Wan, Shaohua Wang, Wenhai Lu, Tong Collage of Computer and Information Hohai University Nanjing China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China Shanghai AI Laboratory Shanghai China National Key Lab for Novel Software Technology Nanjing University Nanjing China

Incremental few-shot semantic segmentation (IFSS) targets at incrementally expanding model’s capacity to segment new class of images supervised by only a few samples. However, features learned on old classes could significantly drift, causing catastrophic forgetting. Moreover, few samples for pixel-level segmentation on new classes lead to notorious overfitting issues in each learning session. In this paper, we explicitly represent class-based knowledge for semantic segmentation as a category embedding and a hyper-class embedding, where the former describes exclusive semantical properties, and the latter expresses hyper-class knowledge as class-shared semantic properties. Aiming to solve IFSS problems, we present EHNet, i.e., Embedding adaptive-update and Hyper-class representation Network from two aspects. First, we propose an embedding adaptive-update strategy to avoid feature drift, which maintains old knowledge by hyper-class representation, and adaptively update category embeddings with a class-attention scheme to involve new classes learned in individual sessions. Second, to resist overfitting issues caused by few training samples, a hyper-class embedding is learned by clustering all category embeddings for initialization and aligned with category embedding of the new class for enhancement, where learned knowledge assists to learn new knowledge, thus alleviating performance dependence on training data scale. Significantly, these two designs provide representation capability for classes with sufficient semantics and limited biases, enabling to perform segmentation tasks requiring high semantic dependence. Experiments on PASCAL-5i and COCO datasets show that EHNet achieves new state-of-the-art performance with remarkable advantages. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

An empirical study on issue knowledge transfer from python to R for machine learning software 32

学校读者我要写书评

暂无评论

An empirical study on issue knowledge transfer from python t...

32nd International Conference on software Engineering and Knowledge Engineering, SEKE 2020

作者： Huang, Wenchin Ji, Zhenlan Li, Yanhui State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Management and Engineering Nanjing University China

ISBN: (纸本)1891706500

Background: With the blowout of programming languages, developers employ different languages to solve similar problems (e.g., to implement machine learning algorithms) separately and frequently, which gives rise to knowledge transfer across different language development. Since GitHub provides an issue tracking system for developers and users to follow with issues, knowledge about how to deal with issues is a main part of available knowledge on GitHub. Such issue knowledge could be directly transferred to help developers handle new issues on current projects from similar projects in different languages. Aims: Inspired by a large amount of developed and developing machine learning software written in Python and R on GitHub, we aim to discover how much issue knowledge can be transferred from Python projects to R projects. Method: We investigate totally 1161 issues from 15 popular machine learning projects in R and 7496 issues from Scikit-Learn in Python on GitHub. After computing the text similarity between issues from R and Python projects, we match top 5 similar Scikit-Learn issues for each R issue and manually judge 1161×5 issue-pairs to label and group them. Results: We observe that a) 13% (149/1161) of R issues can refer to related Python issues;b) 47% (71/149) of related R issues can be linked to Python issues by the text mining technique BM25 at the very early stage;c) 83% (124/149) of related Python issues support code and description about the similar machines learning problems;d) reference knowledge is considered as the most useful knowledge from Python issues. Conclusion: We put forward the following suggestions: a) referring to the corresponding cross languages issues is an efficient way for developers, especially there is the lack of related information in current language;b) the text mining technique BM25 is helpful for developers to start earlier for searching similar issues cross languages. © 2020 Knowledge Systems Institute Graduate School. All rights

关键词： Python

Boosting component-based synthesis with control structure recommendation 1

学校读者我要写书评

暂无评论

Boosting component-based synthesis with control structure re...

1st ACM SIGSOFT International Workshop on Representation Learning for software Engineering and Program Languages, RL+SE and PL 2020, co-located with ESEC/FSE 2020

作者： Liu, Binbin Dong, Wei Zhang, Yating Wang, Daiyan Liu, Jiaxin College of Computer Science National University of Defense Technology Changsha China Key Lab. of Software Engineering for Complex Systems College of Computer Science National University of Defense Technology Changsha China

ISBN: (纸本)9781450381253

Component-based synthesis is an important research field in program synthesis. API-based synthesis is a subfield of component-based synthesis, the component library of which are Java APIs. Unlike existing work in API-based synthesis that can only generate loop-free programs constituted by APIs, state-of-The-Art work FrAngel can generate programs with control structures. However, for the generation of control structures, it samples different types of control structures all at random. Given the information about the desired method (such as method name and input/output types), experienced programmers can have an initial thought about the possible control structures that could be used in implementing the desired method. The knowledge about control structures in the method can be learned from high-quality projects. In this paper, we propose a novel approach of recommending control structures for API-based synthesis based on deep learning. A neural network that can jointly embed the natural language description, method name, and input/output types into high-dimensional vectors to predict the possible control structures of the desired method is proposed. We integrate the prediction model into the synthesizer to improve the efficiency of synthesis. We train our model on a codebase of high-quality Java projects from GitHub. The prediction results of the neural network are fed to the API-based synthesizer to guide the sampling process of control structures. The experimental results on 40 programming tasks show that our approach can effectively improve the efficiency of synthesis. © 2020 ACM.

关键词： Efficiency