检索结果-内蒙古大学图书馆

Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jiangtong Liu, Dongyi Cheng, Dawei Jiang, Changjun School of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education China

Graph Neural Networks (GNNs) have achieved significant success in various real-world applications, including social networks, finance systems, and traffic management. Recent researches highlight their vulnerability to backdoor attacks in node classification, where GNNs trained on a poisoned graph misclassify a test node only when specific triggers are attached. These studies typically focus on single attack categories and use adaptive trigger generators to create node-specific triggers. However, adaptive trigger generators typically have a simple structure, limited parameters, and lack category-aware graph knowledge, which makes them struggle to handle backdoor attacks across multiple categories as the number of target categories increases. We address this gap by proposing a novel approach for Effective and Unnoticeable Multi-Category (EUMC) graph backdoor attacks, leveraging subgraph from the attacked graph as category-aware triggers to precisely control the target category. To ensure the effectiveness of our method, we construct a Multi-Category Subgraph Triggers Pool (MC-STP) using the subgraphs of the attacked graph as triggers. We then exploit the attachment probability shifts of each subgraph trigger as category-aware priors for target category determination. Moreover, we develop a "select then attach" strategy that connects suitable category-aware trigger to attacked nodes for unnoticeability. Extensive experiments across different real-world datasets confirm the efficacy of our method in conducting multi-category graph backdoor attacks on various GNN models and defense strategies. © 2024, CC BY-NC-SA.

关键词： Graph neural networks

Constructing Prioritized Interaction Test Suite with Interaction Relationship

学校读者我要写书评

暂无评论

Constructing Prioritized Interaction Test Suite with Interac...

International Workshop on education Technology and Computer Science, ETCS

作者： Jianjun Yuan Zuowen Jiang The Key Laboratory of Embedded System and Service Department of Computer Science and Technology Computing Ministry of Education of China University of Tongji Shanghai China

ISBN: (纸本)9781424463886;9780769539874

Interaction testing has addressed some issues on how to select a small subset of test cases. In many systems where interaction testing is needed, the entire test suite is not executed because of time or budget constraints. It is important to prioritize the test cases in these situations. On the other hand, there are not always interactions among any factors in real systems. Moreover, some factors may need N-way (N>2) testing since there is a closer relationship among them. We present a model for prioritized interaction testing with interaction relationship and propose a greedy algorithm for generating variable strength covering arrays with bias.

关键词： system testing Software testing Computer science education Greedy algorithms Costs educational technology Computer science laboratories embedded system embedded computing

Detecting and resolving mismatches between pairs of services

学校读者我要写书评

暂无评论

Detecting and resolving mismatches between pairs of services

International Conference on Computer Science and Information Technology (CSIT)

作者： Tao Liu Guosun Zeng Key Laboratory of Embedded System and Service Computing Ministry of Education University of Tongji Shanghai China Tongji University Shanghai Shanghai CN

Facing changing environments and evolving business, service composition happens all time. However, services do not always interact properly because of mismatches between their interfaces. In this paper, we use labelled interface automata, an extension of interface automata, to illustrate mismatching interfaces and resolution approaches. We model service interfaces with labelled interface automata and propose a theorem for mismatch detecting. Then we characterize mismatches between pairs of interfaces by identifying and classifying them into six basic scenarios, and illustrate the resolution approach of mismatches. Our method formalizes the interface adaptation problem and provides convenience to detect mismatches and build adaptors for service interactions.

关键词： Automata Software

Improved Extremal Optimization for Constrained Pairwise Testing

学校读者我要写书评

暂无评论

Improved Extremal Optimization for Constrained Pairwise Test...

International Conference on Research Challenges in Computer Science (ICRCCS)

作者： Jianjun Yuan Changjun Jiang Zuowen Jiang Department of Computer Science and Technology The Key Laboratory of Embedded System and Service Computing Ministry of Education of China University of Tongji Shanghai China

Pairwise testing, which requires that every combination of valid values of each pair of system factors be covered by at lease one test case, plays an important role in software testing since many faults are caused by unexpected 2-way interactions among system factors. In real systems, constraints usually exist between values, which means that some values cannot coexist in a valid test. Although meta-heuristic strategies like simulated annealing can generally discover smaller pairwise test suite in the presence of constraints, they may cost more time to perform search, compared with greedy algorithms. We propose a new method, improved extremal optimization, for constructing constrained pairwise test suites. Experimental results show that improved extremal optimization gives similar size of resulting pairwise test suite and yields a 13% reduction in solution time over simulated annealing.

关键词： Constraint optimization Software testing system testing Simulated annealing Costs Greedy algorithms Computer science educational technology laboratories embedded system

Adaptive finite time stability of delayed systems with applications to network synchronization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Xiwei Department of Computer Science and Technology Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

The finite time stability (FnTSta) theory of delayed systems has not been set up until now. In this paper, we propose a two-phases-method (2PM), to achieve this object. In the first phase, we prove that the time for norm of system error evolving from initial values to 1 is finite;then in the second phase, we prove that the time for norm of the error evolving from 1 to 0 is also finite, thus FnTSta is obtained. Considering the cost and complexity of controller, we use only two simple terms to realize this aim. For the proposed 2PM, time delays can be the same or asynchronous, bounded or unbounded, etc;the norm can be 2-norm, 1-norm, ∞-norm, which show that 2PM is powerful and has a wide scope of applications. Furthermore, we also prove the adaptive finite time stability (AFnTSta) theory of delayed systems using 2PM. As an application of the obtained FnTSta theory, we consider the finite time outer synchronization (FnTOSyn) for complex networks with asynchronous unbounded time delays, corresponding criteria are also obtained. Finally, two numerical examples are given to demonstrate the validity of our theories. Copyright © 2020, The Authors. All rights reserved.

关键词： Synchronization

Battery discharge characteristics of wireless sensors in building applications

学校读者我要写书评

暂无评论

Battery discharge characteristics of wireless sensors in bui...

2012 9th IEEE International Conference on Networking, Sensing and Control, ICNSC 2012

作者： Guo, Wenqi Healy, William M. Zhou, MengChu Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102 United States National Institute of Standards and Technology Gaithersburg MD 20899 United States Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China

ISBN: (纸本)9781467303880

Sensor nodes in wireless networks often use batteries as their source of energy, but replacing or recharging exhausted batteries in a deployed network can be difficult and costly. Therefore, prolonging battery life becomes a principal objective in the design of wireless sensor networks (WSNs). There is little published data that quantitatively analyze a sensor node's lifetime under different operating conditions. This paper presents several experiments to quantify the impact of key wireless sensor network design and environmental parameters on battery performance. Our testbed consists of MicaZ motes, commercial alkaline batteries, and a suite of techniques for measuring battery performance. We evaluate known parameters, such as communication distance, working channel and operating power that play key roles in battery performance. Through extensive real battery discharge measurements, we expect our results to serve as a quantitative basis for future research in designing and implementing battery-efficient sensing applications and protocols. © 2012 IEEE.

关键词： Zigbee

Decomposition based efficient algorithms for knowledge reduction

学校读者我要写书评

暂无评论

ICIC Express Letters 2010年第3期4卷 1025-1032页

作者： Jiao, Na Miao, Duoqian Zhang, Hongyun Department of Computer Science and Technology Ministry of Education of China Tongji University Shanghai 201804 China Key Laboratory of Embedded System and Service Computing Ministry of Education of China Tongji University Shanghai 201804 China

Knowledge reduction, one of essential issues for data mining, has alwaysbeen a, hot topic due to the explosive growth of inform,a,tion. However, whenhandling large-scale data, m,any current knowledge reduction m,ethod,s based, onrough set theory are incapable. In this paper, efficient algorithms forknowledge reduction are put forward, based, on decomposition principle. Theidea, of decomposition is to break a, complex problem, down into a,m,a,ster-problem, and, several sub-problem,s that are simpler, m,orem,a,na,gea,ble and, m,ore solvable by using existing induction methods, thenjoining them, together in order to solve the original problem,. Compared, withsom,e traditional methods, the efficiency of the proposed algorithms can beillustrated by experiments with standard datasets from, UCI database. ICIC International © 2010.

关键词： Rough set theory

Adaptive finite time stability of delayed systems via aperiodically intermittent control and quantized control

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Xiwei Ma, Hailian Department of Computer Science and Technology Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

In this brief, we set up the finite time stability (FnTSta) theory for dynamical systems with bounded timevarying delays via aperiodically intermittent control (AIC) and quantized control (QC). A more general QC is designed in this brief. The bound of time-varying delay is required to be less than the infimum in AIC. Two-phases-method (2PM) is applied to solve the FnTSta for delayed system, i.e., it divides the whole proof process into two phases, one phase is that the process for the norm of system error evolving from initial values to 1, and the other is the process for the norm of system error evolving from 1 to 0. By proving that these two phases both use FnT to realize, the whole FnTSta for system is proved. We also design the adaptive rules and prove its validity rigorously. Furthermore, the obtained theories are used to discuss the finite time synchronization (FnTSyn) of neural networks as an application. Finally, some simulations are given to illustrate the effectiveness of our theoretical result. Copyright © 2020, The Authors. All rights reserved.

关键词： Dynamical systems

Finite time anti-synchronization of complex-valued neural networks with bounded asynchronous time-varying delays

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Xiwei Li, Zihan Department of Computer Science and Technology Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

In this paper, we studied the finite time anti-synchronization of master-slave coupled complex-valued neural networks (CVNNs) with bounded asynchronous time-varying delays. With the decomposing technique and the generalized {ξ, ∞}-norm, several criteria for ensuring the finite-time anti-synchronization are obtained. The whole anti-synchronization process can be divided into two parts: first, the norm of each error state component will change from initial values to 1 in finite time, then from 1 to 0 in fixed time. Therefore, the whole time is finite. Finally, one typical numerical example is presented to demonstrate the correctness of our obtained results. key words: Anti-synchronization, asynchronous, complex-valued neural network, finite time, time-varying delay Copyright © 2019, The Authors. All rights reserved.

关键词： Time varying control systems