检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Luo, Wenjian Wu, Chenwang Zhou, Nan Ni, Li Anhui Province Key Laboratory of Software Engineering in Computing and Communication School of Computer Science and Technology University of Science and Technology of China Hefei Anhui230027 China

Deep neural networks (DNNs) have been widely used in many fields such as images processing, speech recognition;however, they are vulnerable to adversarial examples, and this is a security issue worthy of attention. Because the training process of DNNs converge the loss by updating the weights along the gradient descent direction, many gradient-based methods attempt to destroy the DNN model by adding perturbations in the gradient direction. Unfortunately, as the model is nonlinear in most cases, the addition of perturbations in the gradient direction does not necessarily increase loss. Thus, we propose a random directed attack (RDA) for generating adversarial examples in this paper. Rather than limiting the gradient direction to generate an attack, RDA searches the attack direction based on hill climbing and uses multiple strategies to avoid local optima that cause attack failure. Compared with state-of-the-art gradient-based methods, the attack performance of RDA is very competitive. Moreover, RDA can attack without any internal knowledge of the model, and its performance under black-box attack is similar to that of the white-box attack in most cases, which is difficult to achieve using existing gradient-based attack methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Test Case Generation Based on Invariant Extraction

Test Case Generation Based on Invariant Extraction

引用

International Conference on Wireless communications, Networking and Mobile Computing (WiCom)

作者： Fanping Zeng Qing Cao Liangliang Mao Zhide Chen Department of Computer Anhui Province Key Laboratory of Software in Computer and Communication University of Science and Technology Hefei Anhui China Department of Computer University of Science and Technology Hefei Anhui China

software testing is an effective way to find software errors. Generating a good test suite is the key. A program invariant is a property that is true at a particular program point or points. The property could reflect the program's execution over a test suite. Based on this point, we integrate the random test case generation technique and the invariant extraction technique, achieving automatic test case generation and selection. With the same invariants, compared with the traditional random test case generation technique, the experimental results show that the approach this paper describes can generate a smaller test suite.

关键词： software testing Electronic mail Automatic testing System testing Vehicle crash testing Data mining Costs Programming Automation Application software

来源：评论

学校读者我要写书评

暂无评论

Research on Buffer Overflow Test Based on Invariant

Research on Buffer Overflow Test Based on Invariant

引用

International Conference on Computer and Information Technology (CIT)

作者： Fanping Zeng Minghui Chen Kaitao Yin Xufa Wang Department of Computer Anhui Province Key Laboratory of Software in Computer and Communication University of Science and Technology Hefei Anhui China Department of Computer University of Science and Technology Hefei Anhui China

Buffer overflow (BOF) is one of the major vulnerabilities that lead to non-secure software. Testing an implementation for BOF vulnerabilities is challenging as the underlying reasons of buffer overflow vary widely. This paper presents a novel method for BOF test for ANSI C language, which uses program instrumentation and mutation test technology to test the BOF vulnerabilities, on the basis of analyzing the invariants for BOF vulnerabilities. The implementation shows that it can check the attack of BOF vulnerabilities adequately and accurately, in the circumstances of no large losses in performance.

关键词： Buffer overflow Instruments software testing Genetic mutations Monitoring Probes software libraries Runtime Information technology Performance loss

来源：评论

学校读者我要写书评

暂无评论

Community-based 3-SAT formulas with a predefined solution

arXiv

引用

arXiv 2019年

作者： Hu, Yamin Luo, Wenjian Wang, Junteng Anhui Province Key Laboratory of Software Engineering in Computing and Communication School of Computer Science and Technology University of Science and Technology of China China

It is crucial to generate crafted SAT formulas with predefined solutions for the testing and development of SAT solvers since many SAT formulas from real-world applications have solutions. Although some generating algorithms have been proposed to generate SAT formulas with predefined solutions, community structures of SAT formulas are not considered in these algorithms. Consequently, we propose a 3-SAT formula generating algorithm that not only guarantees the existence of a predefined solution, but also simultaneously considers community structures and clause distributions. The proposed 3-SAT formula generating algorithm controls the quality of community structures through controlling (1) the number of clauses whose variables have a common community, which we call intra-community clauses, and (2) the number of variables that only belong to one community, which we call intra-community variables. For a SAT formula, more intra-community clauses and intracommunity variables, higher quality of community structures. To study the combined effect of community structures and clause distributions on the hardness of SAT formulas, we measure solving runtimes of two solvers, gluHack (a leading CDCL solver) and CPSparrow (a leading SLS solver), on the generated SAT formulas under different groups of parameter settings. Through extensive experiments, we obtain some noteworthy observations on the SAT formulas generated by the proposed algorithm: (1) The community structure has little or no effects on the hardness of SAT formulas with regard to CPSparrow but a strong effect with regard to gluHack. (2) Only when the proportion of true literals in a SAT formula in terms of the predefined solution is 0.5, SAT formulas are hard-to-solve with regard to gluHack;when this proportion is below 0.5, SAT formulas are hard-to-solve with regard to CPSparrow. (3) When the ratio of the number of clauses to that of variables is around 4.25, the SAT formulas are hard-to-solve with regard to both glu

关键词： Hardness

来源：评论

学校读者我要写书评

暂无评论

A simplification method of polymorphic boolean functions

arXiv

引用

arXiv 2017年

作者： Luo, Wenjian Li, Zhifang Anhui Key Laboratory of Software in Computing and Communication School of Computer Science and Technology University of Science and Technology of China Hefei230027 China

Polymorphic circuits are a special kind of circuits which possess multiple build-in functions, and these functions are activated by environment parameters, like temperature, light and VDD. The behavior of a polymorphic circuit can be described by a polymorphic Boolean function. For the first time, this brief presents a simplification method of the polymorphic Boolean function. Copyright © 2017, The Authors. All rights reserved.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

Coverage-preserving Data Gathering in Wireless Sensor Networks

Coverage-preserving Data Gathering in Wireless Sensor Networ...

引用

ACIS International Conference on software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD)

作者： Hongli Xu Liusheng Huang Jumin Wu Yang Wang Depart. of Computer Science and Technology Anhui Province key Laboratory of Software in Computing and Communication University of Science and Technology Hefei China

The power is the most significant resource in wireless sensor nodes, so energy conservation is the most important factor in designing the protocol for sensor networks. In this paper, we study the problem of energy-efficient collection of the physical information from the target area. The coverage-preserving data gathering (CPDG) problem is to build up a tree, which minimizes the total energy consumption, and preserves the original coverage to ensure the result correctness. This problem can be formalized as 0-1 integer linear programming, and solved by an efficient heuristic algorithm. Furthermore, an improved algorithm is also proposed to balance the energy consumption among all the sensor nodes. The experimental results show that CPDG algorithm can conserve the energy about 30% of PEDAP protocol, which is regarded as one of the most efficient data gathering protocols as we know.

关键词： Wireless sensor networks Energy efficiency Energy consumption Heuristic algorithms Monitoring Distributed computing Computer networks Energy conservation Wireless application protocol Integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Imperceptible Adversarial Attack on S Channel of HSV Colorspace

Imperceptible Adversarial Attack on S Channel of HSV Colorsp...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Tong Zhu Zhaoxia Yin Wanli Lyu Jiefei Zhang Bin Luo Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China School of Communication and Electronic Engineering East China Normal University Shanghai China

Deep neural network models are vulnerable to subtle but adversarial perturbations that alter the model. Adversarial perturbations are typically computed for RGB images and, therefore, are evenly distributed among RGB channels. Compared with RGB images, HSV images can express the Hue, saturation, and brightness more intuitively. We find that the adversarial perturbation in the S-channel ensures a high attack success rate, while the perturbation is small, and the visual quality of the adversarial examples is good. Using this finding, we propose an attack method, SPGD, to improve the visual quality of adversarial examples by generating perturbations on the S-channel. Based on the attack principle of the PGD method, the RGB image was converted into an HSV image. The gradient calculated by the model on the S channel was superimposed on the S channel and then combined with the non-interference H and V channels to convert back to the RGB image. The iteration stops until the attack succeed. We compare the SPGD method with the existing state-of-the-art attack methods. The results show that SPGD minimizes pixel perturbation while maintaining a high attack success rate and achieves the best results in terms of structural similarity, imperceptibility, the minimum number of iterations, and the shortest run time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Energy-Aware Coverage Based Node Scheduling Scheme for Wireless Sensor Networks

An Energy-Aware Coverage Based Node Scheduling Scheme for Wi...

引用

The 9th International Conference for Young Computer Scientists(第九届国际青年计算机大会)

作者： Jinxia Liu Naijie Gu Songsong He Dept. of Computer Science and Technology University of Science and Technology of China Hefei Anhui 230027 China Anhui Province Key Laboratory of Computing and Communication Software Hefei Anhui 230027 China

A fundamental issue in wireless sensor network is to extend network lifetime while maintaining network coverage and connectivity. Protection for sensors themselves is another important concern. An Energyaware Coverage based Node Scheduling scheme (ECNS) is proposed to provide protection for sensors and guarantees network connectivity and desired coverage level. ECNS enables each node to decide whether it is eligible to turn off to conserve energy through local information exchange with its neighbors. Simulation results show that ECNS improves network performance with respect to energy conservation, load balance and network lifetime.

关键词： Sensor network coverage network connectivity lifetime node scheduling scheme.

来源：评论

学校读者我要写书评

暂无评论

A Hormone-based Clustering Algorithm in Wireless Sensor Networks

A Hormone-based Clustering Algorithm in Wireless Sensor Netw...

引用

2010 2nd International Conference on Computer Engineering and Technology(2010年第二届计算机工程与技术国际会议 ICCET 2010)

作者： Dayuan Dong Haifeng You Yipeng Zhang Xufa Wang Key Laboratory of Software in Computing and Communication Anhui Province School of Computer Science and Technology University of Science and Technology of China HefeiChina

ISBN: (纸本)9781424463473;9781424463497;9781424463503

Clustering problem is one of the hottest issues in wireless sensor networks (WSNs). The strategy for selection of cluster head has not been sufficiently investigated. In this paper,we propose a hormone-based clustering algorithm (HCA) inspired by the communication mechanism of bioendocrine system to prolong the lifetime of the sensor nodes. Two kinds of hormones,cluster hormone and member hormone,are used in the algorithm. Hormone message can promote a node to become a cluster head or a member node. Comparative experiment shows that the proposed algorithm has effectively prolong the lifetime of WSN compared with LEACH[1] and HEED[2].

关键词： hormone:clustering:wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Adversarial Example Defense via Perturbation Grading Strategy

arXiv

引用

arXiv 2022年

作者： Zhu, Shaowei Lyu, Wanli Li, Bin Yin, Zhaoxia Luo, Bin Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China School of Communication & Electronic Engineering East China Normal University Shanghai China

Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researchers have proposed various defense methods to protect DNNs, such as reducing the aggressiveness of adversarial examples by preprocessing or improving the robustness of the model by adding modules. However, some defense methods are only effective for small-scale examples or small perturbations but have limited defense effects for adversarial examples with large perturbations. This paper assigns different defense strategies to adversarial perturbations of different strengths by grading the perturbations on the input examples. Experimental results show that the proposed method effectively improves defense performance. In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：