The rapid growth of online social networks has created significant opportunities for large-scale information dissemination, where many users seek to maximize the visibility and influence of their information, bringing significant attention to the problem of influence maximization (IM). IM aims to identify a limited set of influential users (seed nodes) to maximize information spread. However, existing IM approaches typically provide a unified solution for all users under a fixed seed budget, without considering that different users in real-world scenarios have inherently different target diffusion ranges and seed budgets. Such omissions lead to inefficiency and resource waste, particularly when excessive seed budgets are allocated to users with low diffusion demands. To overcome this issue, we introduce Personalized Influence Maximization (PIM) as an extension of classical IM. Building upon this formulation, we propose the Adaptive Graph Influencer Generator (AGIG), which models seed set selection as a sequence generation task and employs a causal transformer to autoregressively generate personalized and cost-effective seed sets tailored to diverse demands of users. In particular, AGIG incorporates an enhanced dual-view influence encoder that models realistic scenarios where information can reach users without direct connections but with similar interests, thereby strengthening node representations for high-quality seed generation. For effective training, we construct the Propagation Pathways Sequence Dataset by simulating diffusion processes under multiple classical diffusion models and graph structures, enabling AGIG to learn diverse propagation patterns across varying diffusion settings. Extensive experiments demonstrate that AGIG effectively adapts to diverse personalized propagation requirements, achieving an average improvement of approximately 15% in influence spread and cost efficiency over strong baseline methods across multiple datasets and diffusion settings.

Federated graph learning (FGL) collaboratively learns a global graph neural network with distributed graphs, where a significant challenge is addressing non-IID issues. Existing work has not fully explored and utilized the intrinsic features of graphs, resulting in their inability to effectively solve non-IID issues. To tackle this challenge, we investigate for the first time the various heterogeneity that causes non-IID issues in FGL and how they can be utilized to alleviate the issues, including the heterogeneity of nodes and structures as basic components of the graph, as well as the resulting heterogeneity in the representations of the graph. Furthermore, we propose ProtoFGL to address these issues. ProtoFGL first extracts heterogeneous features of nodes and structures from local data and incorporates them into prototypes, which are then used as graph representations for collaborative training. Experimental results show that ProtoFGL outperforms state-of-the-art methods in node classification tasks in accuracy and F1 score.

Graph neural networks (GNNs) have a wide range of applications in multimedia. Recent studies have shown that Graph neural networks (GNNs) are vulnerable to link stealing attacks, which infers the existence of edges in the target GNN's training graph. Existing attacks are usually based on the assumption that links exist between two nodes that share similar posteriors; however, they fail to focus on links that do not hold under this assumption. To this end, we propose LinkThief, an improved link stealing attack that combines generalized structure knowledge with node similarity, in a scenario where the attackers' background knowledge contains partially leaked target graph and shadow graph. Specifically, to equip the attack model with insights into the link structure spanning both the shadow graph and the target graph, we introduce the idea of creating a Shadow-Target Bridge Graph and extracting edge subgraph structure features from it. Through theoretical analysis from the perspective of privacy theft, we first explore how to implement the aforementioned ideas. Building upon the findings, we design the Bridge Graph Generator to construct the Shadow-Target Bridge Graph. Then, the subgraph around the link is sampled by the Edge Subgraph Preparation Module. Finally, the Edge Structure Feature Extractor is designed to obtain generalized structure knowledge, which is combined with node similarity to form the features provided to the attack model. Extensive experiments validate the correctness of theoretical analysis and demonstrate that LinkThief still effectively steals links without extra assumptions. Our code is available at https://github.com/octopusStar218/LinkThief-MM2024.

Federal Learning (FL) is highly respected for protecting data privacy in a distributed environment. However, the correlation between the updated gradient and the training data opens up the possibility of data reconstruction for malicious attackers, thus threatening the basic privacy requirements of FL. Previous research on such attacks mainly focuses on two main perspectives: one exclusively relies on gradient attacks, which performs well on small-scale data but falter with large-scale data; the other incorporates images prior but faces practical implementation challenges. So far, the effectiveness of privacy leakage attacks in FL is still far from satisfactory. In this paper, we introduce the Gradient Guided Diffusion Model (GGDM), a novel learning-free approach based on a pre-trained unconditional Denoising Diffusion Probabilistic Models (DDPM), aimed at improving the effectiveness and reducing the difficulty of implementing gradient based privacy attacks on complex networks and high-resolution images. To the best of our knowledge, this is the first work to employ the DDPM for privacy leakage attacks of FL. GGDM capitalizes on the unique nature of gradients and guides DDPM to ensure that reconstructed images closely mirror the original data. In addition, in GGDM, we elegantly combine the gradient similarity function with the Stochastic Differential Equation (SDE) to guide the DDPM sampling process based on theoretical analysis, and further reveal the impact of common similarity functions on data reconstruction. Extensive evaluation results demonstrate the excellent generalization ability of GGDM. Specifically, compared with state-of-the-art methods, GGDM shows clear superiority in both quantitative metrics and visualization, significantly enhancing the reconstruction quality of privacy attacks.

The knowledge graph (KG) is an efficient form of knowledge organization and expression, providing prior knowledge support for various downstream tasks, and has received extensive attention in natural language processing. However, existing large-scale KGs have many hidden facts that need to be discovered. How to effectively use the structure information of KG is an important research direction of knowledge reasoning. Structure-Information-based reasoning over the KG is a technique used to find the missing facts by the structure information of KG. This survey summarizes the methods and applications of Structure-Information-based reasoning and hopes to be helpful to the research in this field. First, we introduced the definition of knowledge reasoning and the conceptual description of related tasks. Then, we reviewed the methods of Structure-Information-based reasoning. Specifically, we categorized them into four representative classes: PRA-based reasoning, Path-Embedding-based reasoning, RL-based reasoning, and GNN-based reasoning. We compared the motivations and details between practices in the same category. After that, we described the application of Structure-Information-based knowledge reasoning in the KG Completion, Question Answering System, Recommendation System, and other fields. Finally, we discussed the future research directions of Structure-Information-based reasoning.

Knowledge graph embedding technique is one of the mainstream methods to handle the link prediction task, which learns embedding representations for each entity and relation to predict missing links in knowledge graphs. In general, previous convolution-based models apply convolution filters on the reshaped input feature maps to extract expressive features. However, existing convolution-based models cannot extract the interaction information of entities and relations among the same and different dimensional entries simultaneously. To overcome this problem, we propose a novel convolution-based model (SimulE), which utilizes two paths simultaneously to capture the rich interaction information of entities and relations. One path uses 1D convolution filters on 2D reshaped input maps, which maintains the translation properties of the triplets and has the ability to extract interaction information of entities and relations among the same dimensional entries. Another path employs 3D convolution filters on the 3D reshaped input maps, which is suitable for capturing the interaction information of entities and relations among the different dimensional entries. Experimental results show that SimulE can effectively model complex relation types and achieve state-of-the-art performance in almost all metrics on three benchmark datasets. In particular, compared with baseline ConvE, SimulE outperforms it in MRR by 2.9%, 9.8% and 2.8% on FB15k-237, YAGO3-10 and DB100K respectively.

Software Defined Networking (SDN) provides flexibility and programmability for network management by using a layered structure composed of data plane, control plane, and application plane. A key enabling technique for the sustainability of SDN-based network infrastructure is the modeling of power consumed by SDN control planes. However, power modeling of control planes is not extensively investigated yet, and no generic methods have been developed for performance and power comparison of sustainable SDN control planes. In this paper, we propose analytical performance and power models for different network controllers by using queuing theory, and design a generic framework for performance and power evaluation of different sustainable SDN control planes. Extensive simulation results show that the proposed solution can precisely model the power and performance of the concerned SDN control planes such that different control planes can be benchmarked under a general framework, which enables the identification of suitable control planes for various SDN network applications.

With the emergence of hybrid software-defined network (SDN) that contains switches and all kinds of middleboxes, there are a lot of obvious problems that have been brought up in verifying data plane consistency. However, recent study in network verification neglected the dynamic data plane verification induced by stateful middleboxes. To handle this limitation, we propose a new method, Stateful Header Space Analysis (SHSA), to verify reachability and detect loops in hybrid software-defined network with stateful middleboxes. Moreover, we optimize the validation process on the base of header space analysis (HSA) and enhance the scalability of our verification algorithm. To validate the applicability of SHSA, we implement four kinds of stateful middleboxes by Open vSwitch and simulate the hybrid network. The experimental results indicate that our method could verify the dynamic data plane accurately. Compared the time cost between SHSA and HSA in Stanford University's backbone network, results show that the efficiency of our method is 30 percent higher than the latter approximately.

With the increasing scale of cloud datacenters, the volumes of traffic flows inside a single datacenter become larger. An effective virtual machine (VM) replacement among physical machines (PMs) can improve resource utilization rate and reduce overall network cost in cloud datacenters. In this paper, we propose a Modified Max-Min Ant Colony Optimization (M3ACO) algorithm which can be used to solve the VMs replacement problem. Furthermore, we apply the M3ACO algorithm into a new framework based on Software Defined Network (SDN), which provides an integrated solution for resource optimization problem in cloud datacenters.

Unstructured Peer-to-Peer networks support uncoupled data placements, elaborate semantic queries and highly dynamic scenario. These properties make such systems extraordinary suitable for applications of mass-market decentralized file sharing, which is still the most dominant application currently in use on current P2P-powered systems. In this paper, we propose SSplus, a novel search algorithm extended from our previously developed Smart Search algorithm, focusing on improving the search efficiency and the network utilization in unstructured P2P file-sharing systems. We achieve these goals by introducing several novel techniques below as enhancements: (a) Load Balancing based on Free Availability, (b) Intelligent 2-Level Replication, and (c) Resources Booking and Reservation. Extensive simulations under realistic conditions substantiate significant performance gains of SSplus, compared with the original Smart Search algorithm.

Gnutella-like Peer-to-Peer Networks, due to their extreme connectivity fluctuations, are highly robust against random failures. However, such error tolerance comes at a high price of attack survivability. In this paper, to enhance such attack survivability, we propose a new formulation used for defense against deliberately attacks based on two leading concepts: cost and load. The cost measures how expensive it is to cure an attacked or infected node, and the load measures how important a link between two nodes is when propagating attacks or updating immunization information reversely. The combination of these factors leads us to introduce the concept of optimal targeted immunization, which formalizes the ideas of minimizing the risk of epidemic outbreaks in these networks. Using this analysis framework, we then devise a novel efficient targeted immunization scheme. The simulation results under a realistic Gnutella network show that our immunization scheme outperforms other existing methods, producing an arresting increase of the network attack tolerance at a lower price of eliminating malicious attacks.

The paper presents secure protocols and new secure challenges based on looser radio propagation assumptions. According to these, a new secure enhancement mechanism for secure protocols is proposed. Then we exemplify the DoS attacks and protections as the illustration. The research indicates it will increase the usability of secure protocols in common applications.