检索结果-内蒙古大学图书馆

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

Improved Sparse Activity Detection Based on Optimized Measurement Matrix in mMTC

学校读者我要写书评

暂无评论

Improved Sparse Activity Detection Based on Optimized Measur...

IEEE Conference on Vehicular technology (VTC)

作者： Jianyu Wang Liu Yang Chaoyuan Bai Heng Liu Communication and Sensor Network for Modern Transportation International Cooperation Center(CSNMT) Southwest Jiaotong University Chengdu P.R.China Key Lab of Information Coding & Transmission Institude of Mobile Communication Southwest Jiaotong University Chengdu P.R.China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu P.R.China

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Device activity detection and channel estimation are central problems in massive Machine Type Communication (mMTC) scenarios. Given the sparse distribution of active devices, compressive sensing (CS) emerges as a viable solution at the gNB to mitigate interference stemming from non-orthogonal preamble sets. This paper proposes an algorithm for optimizing measurement matrix, thereby elevating the performance of signal recovery in CS. Within the proposed algorithm, a optimization model that integrates eigenvalue averaging and equiangular tight frame (ETF) theory is formulated, and an iterative algorithm is devised to approximate the optimal solution utilizing singular value decomposition (SVD). Further, a weight-based strategie is discussed with respect to the feasibility of the proposed algorithm, accompanied by the introduction of iteration termination condition. Experimental results corroborate the algorithm’s swift convergence, underpinning the efficient production of high-performance matrices that refine the accuracy of joint device activity detection and channel estimation.

关键词： Vehicular and wireless technologies Optimization models Channel estimation Approximation algorithms Eigenvalues and eigenfunctions Sparse matrices Matrix decomposition Optimization Convergence Singular value decomposition

Utility maximization for multihop wireless networks employing BATS codes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dong, Yanyan Jin, Sheng Chen, Yanzuo Yang, Shenghao Yin, Hoover H.F. The School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Carnegie Mellon University The N-hop Technologies Limited Hong Kong The Institute of Network Coding The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Shenzhen Research Institute of Big Data Shenzhen China

BATS (BATched Sparse) codes are a class of efficient random linear network coding variation that has been studied for multihop wireless networks mostly in scenarios of a single communication flow. Towards sophisticated multi-flow network communications, we formulate a network utility maximization (NUM) problem that jointly optimizes the BATS code parameters of all the flows and network scheduling. The NUM problem adopts a batch-wise packet loss model that can be obtained from the network local statistics without any constraints on packet loss patterns. Moreover, the NUM problem allows a different number of recoded packets to be transmitted for different batches in a flow, which is called adaptive recoding. Due to both the probably nonconcave objective and the BATS code-related variables, the algorithms developed for the existing flow optimization problems cannot be applied directly to solve our NUM problem. We introduce a two-step algorithm to solve our NUM problem, where the first step solves the problem with nonadaptive recoding schemes, and the second step optimizes adaptive recoding hop-by-hop from upstream to downstream in each flow. We perform various numerical evaluations and simulations to verify the effectiveness and efficiency of the algorithm. © 2021, CC BY-NC-ND.

关键词： Packet loss

Small-sample inferred adaptive recoding for batched network coding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Jie Jia, Zhiyuan Yin, Hoover H.F. Yang, Shenghao School of Science and Engineering Chinese University of Hong Kong Shenzhen Shenzhen Hong Kong Institute of Network Coding Chinese University of Hong Kong Hong Kong Hong Kong H.Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta United States Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Shenzhen China

Batched network coding is a low-complexity network coding solution to feedbackless multi-hop wireless packet network transmission with packet loss. The data to be transmitted is encoded into batches where each of which consists of a few coded packets. Unlike the traditional forwarding strategy, the intermediate network nodes have to perform recoding, which generates recoded packets by network coding operations restricted within the same batch. Adaptive recoding is a technique to adapt the fluctuation of packet loss by optimizing the number of recoded packets per batch to enhance the throughput. The input rank distribution, which is a piece of information regarding the batches arriving at the node, is required to apply adaptive recoding. However, this distribution is not known in advance in practice as the incoming link's channel condition may change from time to time. On the other hand, to fully utilize the potential of adaptive recoding, we need to have a good estimation of this distribution. In other words, we need to guess this distribution from a few samples so that we can apply adaptive recoding as soon as possible. In this paper, we propose a distributionally robust optimization for adaptive recoding with a small-sample inferred prediction of the input rank distribution. We develop an algorithm to efficiently solve this optimization with the support of theoretical guarantees that our optimization's performance would constitute as a confidence lower bound of the optimal throughput with high probability. Copyright © 2021, The Authors. All rights reserved.

关键词： network coding

A unified adaptive recoding framework for Batched network coding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yin, Hoover H.F. Tang, Bin Ng, Ka Hei Yang, Shenghao Wang, Xishi Zhou, Qiaoqiao The N-hop Technologies Limited Hong Kong The Institute of Network Coding The Chinese University of Hong Kong Hong Kong The School of Computer and Information Hohai University Nanjing China The Department of Physics The Chinese University of Hong Kong Hong Kong The School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Shenzhen Research Institute of Big Data Shenzhen China The Department of Information Engineering The Chinese University of Hong Kong Hong Kong

Batched network coding is a variation of random linear network coding which has low computational and storage costs. In order to adapt to random fluctuations in the number of erasures in individual batches, it is not optimal to recode and transmit the same number of packets for all batches. Different distributed optimization models, which are called adaptive recoding schemes, were formulated for this purpose. The key component of these optimization problems is the expected value of the rank distribution of a batch at the next network node, which is also known as the expected rank. In this paper, we put forth a unified adaptive recoding framework with an arbitrary recoding field size. We show that the expected rank functions are concave when the packet loss pattern is a stationary stochastic process, which covers but not limited to independent packet loss and Gilbert-Elliott packet loss model. Under this concavity assumption, we show that there always exists a solution which not only can minimize the randomness on the number of recoded packets but also can tolerate rank distribution errors due to inaccurate measurements or limited precision of the machine. We provide an algorithm to obtain such an optimal optimal solution, and propose tuning schemes that can turn any feasible solution into a desired optimal solution. © 2021, CC BY-NC-ND.

关键词： Packet loss

BAR: Blockwise adaptive recoding for batched network coding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yin, Hoover H.F. Yang, Shenghao Zhou, Qiaoqiao Yung, Lily M.L. Ng, Ka Hei The Institute of Network Coding The Chinese University of Hong Kong Hong Kong Hong Kong The School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen China Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Shenzhen Research Institute of Big Data Shenzhen China The Department of Information Engineering The Chinese University of Hong Kong Hong Kong Hong Kong The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong The Department of Physics The Chinese University of Hong Kong Hong Kong Hong Kong

Multi-hop networks become popular network topologies in various emerging Internet of things applications. Batched network coding (BNC) is a solution to reliable communications in such networks with packet loss. By grouping packets into small batches and restricting recoding to the packets belonging to the same batch, BNC has a much smaller computational and storage requirements at the intermediate nodes compared with a direct application of random linear network coding. In this paper, we propose a practical recoding scheme called blockwise adaptive recoding (BAR) which learns the latest channel knowledge from short observations so that BAR can adapt to the fluctuation of channel conditions. We focus on investigating practical concerns such as the design of efficient BAR algorithms. We also design and investigate feedback schemes for BAR under imperfect feedback systems. Our numerical evaluations show that BAR has significant throughput gain for small batch size compared with the existing baseline recoding scheme. More importantly, this gain is insensitive to inaccurate channel knowledge. This encouraging result suggests that BAR is suitable to be realized in practice as the exact channel model and its parameters could be unknown and subject to change from time to time. Copyright © 2021, The Authors. All rights reserved.

关键词： network coding

Intrablock interleaving for Batched network coding with blockwise adaptive recoding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yin, Hoover H.F. Ng, Ka Hei Zhong, Allen Z. Yeung, Raymond W. Yang, Shenghao Chan, Ian Y.Y. The N-hop Technologies Limited Hong Kong The Institute of Network Coding The Chinese University of Hong Kong Hong Kong The Department of Information Engineering The Chinese University of Hong Kong Hong Kong Limited The Department of Physics The Chinese University of Hong Kong Hong Kong The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Shenzhen Research Institute of Big Data Shenzhen China The Department of Economics The Chinese University of Hong Kong Hong Kong

Batched network coding (BNC) is a low-complexity solution to network transmission in multi-hop packet networks with packet loss. BNC encodes the source data into batches of packets. As a network coding scheme, the intermediate nodes perform recoding on the received packets belonging to the same batch instead of just forwarding them. A recoding scheme that may generate more recoded packets for batches of a higher rank is also called adaptive recoding. Meanwhile, in order to combat burst packet loss, the transmission of a block of batches can be interleaved. Stream interleaving studied in literature achieves the maximum separation among any two consecutive packets of a batch, but permutes packets across blocks and hence cannot bound the buffer size and the latency. To resolve the issue of stream interleaver, we design an intrablock interleaver for adaptive recoding that can preserve the advantages of using a block interleaver when the number of recoded packets is the same for all batches. We use potential energy in classical mechanics to measure the performance of an interleaver, and propose an algorithm to optimize the interleaver with this performance measure. Our problem formulation and algorithm for intrablock interleaving are also of independent interest. © 2021, CC BY-NC-ND.

关键词： network coding

Improved Upper Bound on the network Function Computing Capacity

学校读者我要写书评

暂无评论

Improved Upper Bound on the Network Function Computing Capac...

作者： Guang, Xuan Yeung, Raymond W. Yang, Shenghao Li, Congduan School of Mathematical Sciences and LPMC Nankai University Tianjin300071 China Institute of Network Coding Chinese University of Hong Kong Hong Kong Hong Kong Department of Information Engineering Chinese University of Hong Kong Hong Kong Hong Kong School of Science and Engineering Chinese University of Hong Kong Shenzhen518172 China Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China School of Electronics and Communication Engineering Sun Yat-sen University Guangzhou510006 China

The problem of network function computation over a directed acyclic network is investigated in this paper. In such a network, a sink node desires to compute with zero error a target function, of which the inputs are generated at multiple source nodes. The edges in the network are assumed to be error-free and have limited capacity. The nodes in the network are assumed to have unbounded computing capability and be able to perform network coding. The computing rate of a network code that can compute the target function over the network is the average number of times that the target function is computed with zero error for one use of the network. In this paper, we obtain an improved upper bound on the computing capacity, which is applicable to arbitrary target functions and arbitrary network topologies. This improved upper bound not only is an enhancement of the previous upper bounds but also is the first tight upper bound on the computing capacity for computing an arithmetic sum over a certain non-tree network, which has been widely studied in the literature. We also introduce a multi-dimensional array approach that facilitates evaluation of the improved upper bound. Furthermore, we apply this bound to the problem of computing a vector-linear function over a network. With this bound, we are not only able to enhance a previous result on computing a vector-linear function over a network but also simplify the proof significantly. Finally, we prove that for computing the binary maximum function over the reverse butterfly network, our improved upper bound is not achievable. This result establishes that in general our improved upper bound is non-achievable, but whether it is asymptotically achievable or not remains open. © 1963-2012 IEEE.

关键词： network coding

Comments on cut-set bounds on network function computation

学校读者我要写书评

暂无评论

Comments on cut-set bounds on network function computation

作者： Huang, Cupjin Tan, Zihan Yang, Shenghao Guang, Xuan Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Department of Computer Science University of Chicago ChicagoIL60637 United States School of Science and Engineering Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen518172 China School of Mathematical Sciences and LPMC Nankai University Tianjin China Institute of Network Coding Chinese University of Hong Kong Hong Kong Hong Kong

A function computation problem over a directed acyclic network has been considered in the literature, where a sink node is required to compute a target function correctly with the inputs arbitrarily generated at multiple source nodes. The network links are error free but capacity limited, and the intermediate nodes perform network coding. The computing rate of a network code is the average number of times that the target function is computed for one use of the network, i.e., each link in the network is used at most once. In the existing papers, two cut-set bounds were proposed on the computing rate. However, we in this paper show that these bounds are not valid for general network function computation problems. We analyze the reason of the invalidity and propose a general cut-set bound by using a new equivalence relation associated with the inputs of the target function. Moreover, some results in the existing papers were proved by applying the invalid upper bound. We also justify the validity of these results. © 1963-2012 IEEE.

关键词： network coding