The rapid growth of Internet of Things (IoT) devices has heightened hardware security concerns, particularly with the emergence of hardware Trojans (HTs) as malicious components in integrated circuits. These HTs pose significant threats to information privacy and system performance. The early detection methods rely on golden references and domain knowledge, limiting their implementation in large-scale integrated circuits. Traditional machine learning-based HT detections can effectively identify infected circuits without golden chips. However, locating and evaluating the specific behavior of HTs in vast and complex circuits is challenging. To address these challenges, this paper presents an HT Object Detection (HTOD) problem, which involves two primary tasks: identifying the boundaries and sizes of HTs within circuits and distinguishing between different HT behaviors. We have developed a two-stage HT object detection framework based on a bidirectional jumping knowledge network called HTOD-BGNN to solve the HTOD problem, which enables progressive refinement of localized regions. It incorporates enhanced base-type features to ensure scalability and information retention during modeling. Additionally, the implementation of sample augmentation alleviates the challenges of sample imbalance and scarcity. The proposed method enables more intelligent circuit detection, achieving 100% and 87.5% detection rates for Trojan triggering and payload behaviors, respectively. It demonstrates superior localization performance and effective generalization to unseen circuit scenarios via its region refinement mechanism, achieving F1-scores of 54.01% on TrustHub and 90.04% on TRIT datasets.

Various datacenter network (DCN) load balancing schemes have been proposed in the past decade. Unfortunately, most of these solutions designed for lossy DCNs do not work well for Priority Flow Control (PFC) enabled lossless DCNs, primarily due to the reason that the individual congestion signals used in these solutions, e.g., link load, queue length, Round Trip Time (RTT) and Explicit Congestion Notification (ECN), may not be able to correctly or timely reflect the hop-by-hop PFC pausing. This paper first reveals the above problems via extensive experiments, and then based on the insights learned, we present Proteus, a PFC-aware load balancing scheme that is resilient to PFC pausing by exploring a combination of multi-level congestion signals. At its heart, Proteus leverages RTT-level signals (i.e., RTT and link utilization) to detect path status for initial routing decision, and exploits sub-RTT level signal (i.e., cumulative sojourn time) to reflect instantaneous PFC pausing and make timely rerouting choices based on the idea of better-late-than-never. We have implemented Proteus in the hardware programmable switch. Our testbed experiments as well as large-scale simulations show that Proteus can effectively handle PFC pausing under realistic workloads and achieve up to 35%, 31%, 28%, 22% and 46%, 42%, 34%, 29% better average FCT and$99^{th}$percentile FCT than CONGA, DRILL, Hermes and MP-RDMA, respectively.

Today's trend of building ever larger language models (LLMs), while pushing the performance of natural language processing, adds significant latency to the inference stage. We observe that due to the diminishing returns of adding parameters to LLMs, a smaller model could make the same prediction as a costly LLM for a majority of queries. Based on this observation, we design Tabi, an inference system with a multi-level inference engine that serves queries using small models and optional LLMs for demanding applications. Tabi is optimized for discriminative models (i.e., not generative LLMs) in a serving framework. Tabi uses the calibrated confidence score to decide whether to return the accurate results of small models extremely fast or re-route them to LLMs. For re-routed queries, it uses attention-based word pruning and weighted ensemble techniques to offset the system overhead and accuracy loss. We implement and evaluate Tabi with multiple tasks and models. Our result shows that Tabi achieves 21%-40% average latency reduction (with comparable tail latency) over the state-of-the-art while meeting LLM-grade high accuracy targets.

Various datacenter network (DCN) load balancing schemes have been proposed in the past decade. Unfortunately, most of these solutions designed for lossy DCNs do not work well for Priority Flow Control (PFC) enabled lossless DCNs, primarily due to the reason that the individual congestion signals used in these solutions, e.g., link load, queue length, Round Trip Time (RTT) and Explicit Congestion Notification (ECN), may not be able to correctly or timely reflect the hop-by-hop PFC pausing. This paper first reveals the above problems via extensive experiments, and then based on the insights learned, we present Proteus, a PFC-aware load balancing scheme that is resilient to PFC pausing by exploring a combination of multi-level congestion signals. At its heart, Proteus leverages RTT-Ievel signals (i.e., RTT and link utilization) to detect path status for initial routing decision, and exploits sub-RTT level signal (i.e., cumulative sojourn time) to reflect instantaneous PFC pausing and make timely rerouting choices based on the idea of better-late-than-never. We have implemented Proteus in the hardware programmable switch. Our testbed experiments as well as large-scale simulations show that Proteus can effectively handle PFC pausing under realistic workloads and achieve up to 35 %, 31 %, 28%, 22% and 46 %, 42 %, 34 %, 29 % better average FCT and 99thpercentile FCT than CONGA, DRILL, Hermes and MP-RDMA, respectively.

Graph neural networks (GNNs) have been applied successfully in many machine learning tasks due to their advantages in utilizing neighboring information. Recently, with the global enactment of privacy protection regulations, federated GNNs have gained increasing attention in academia and industry. However, the graphs owned by different participants could be non-independently-and-identically distributed (non-IID), leading to the deterioration of federated GNNs' accuracy. In this paper, we propose a globally consistent federated graph autoencoder (GCFGAE) to overcome the non-IID problem in unsupervised federated graph learning via three innovations. First, by integrating federated learning with split learning, we train a unique global model instead of FedAvg-styled global and local models, yielding results consistent with that of the centralized GAE. Second, we design a collaborative computation mechanism considering overlapping vertices to reduce communication overhead during forward propagation. Third, we develop a layer-wise and block-wise gradient computation strategy to reduce the space and communication complexity during backward propagation. Experiments on real-world datasets demonstrate that GCFGAE achieves not only higher accuracy but also around 500 times lower communication overhead and 1000 times smaller space overhead than existing federated GNN models.

In order to provide more efficient and reliable power services than the traditional grid, it is necessary for the smart grid to accurately predict the electric load. Recently, recurrent neural networks (RNNs) have attracted increasing attention in this task because it can discover the temporal correlation between current load data and those long-ago through the self-connection of the hidden layer. Unfortunately, the traditional RNN is prone to the vanishing or exploding gradient problem with the increase of memory depth, which leads to the degradation of predictive accuracy. Many RNN architectures address this problem at the expense of complex internal structures and increased network parameters. Motivated by this, this article proposes two adaptive modularized RNNs to tackle the challenge, which can not only solve the gradient problem effectively with a simple architecture, but also achieve better performance with fewer parameters than other popular RNNs.

Community detection is an important research direction in complex network analysis that can help us discover valuable network structures. The community detection algorithms based on multiobjective particle swarm optimization encode community membership of nodes in particles and employ evolutionary strategies to search for the optimal community division. Existing algorithms face two challenges: (1) they are inapplicable to large networks because the evolution process is time-consuming; (2) they are easy to fall into local optima. In this paper, we propose a novel algorithm that combines a label-propagation-based multiobjective particle swarm optimization algorithm with a graph attention variational autoencoder to realize community detection. On the one hand, the label propagation strategy is involved in the update of a swarm's particles to speed up its evolution. The optimal solutions found by the particle swarm optimization algorithm are embedded into the objective of the autoencoder to improve the embedding vectors’ quality. On the other hand, the embedding vectors are used to improve the solutions of the particle swarm optimization algorithm to avoid its early convergence. The experiments on artificial and real-world networks demonstrate the feasibility and effectiveness of our algorithm compared with some state-of-the-art algorithms.

Community detection is a fundamental problem in complex network analysis that aims to find closely related groups of nodes. Recently, network embedding techniques have been integrated into community detection in two manners to capture the intricate relationships between nodes. The two-staged manner generates node embedding vectors and obtains communities by running a clustering algorithm on them. The single-staged manner simultaneously obtains node embedding vectors and communities by optimizing a hybrid objective concerning with node–community relationships. The general-purpose network embedding algorithms used in the first manner do not emphasize retaining node–community relationships. The second manner ignores the influence of a node’s location in a community (at the center or boundary) and its attributes on community generation. In this article, we propose a biased-random-walk-based community detection (BRWCD) algorithm to tackle the issues. First, a topology-weighted degree is designed to enhance the random walk at the boundary of and inside a community to extract communities precisely. Second, we design an attribute-to-node influence index and an attribute-weighted degree to distinguish different attributes’ influence on node transition to obtain communities with high internal cohesion. Comprehensive experiments on the real-world and synthetic networks demonstrate that BRWCD achieves nearly 10% higher accuracy at most than the state-of-the-art algorithms.

Community structure is a typical characteristic of complex networks. Finding communities in complex networks has many important applications, such as the advertisement and recommendation based on social networks and the discovery of new protein molecules in biological networks, which make it a hot topic in the field of complex network analysis. With the increasing concerns about the leakage of personal privacy, discovering communities spread across the local networks owned by multiple participants accurately while preserving each participant’s privacy has become an emerging challenge in distributed community detection. In this article, we propose a general federated graph learning model for privacy-preserving distributed graph learning and develop two federated clique percolation algorithms (CPAs) based on it to discover overlapping communities distributed across multiple participants’ local networks without disclosing any participant’s network privacy. Homomorphic encryption and hash operation are used in combination to protect the privacy of the vertices and edges of each local network. Furthermore, vertex attributes are involved in the calculation of clique similarity and clique percolation when dealing with attributed networks. The experimental results on real-world and artificial datasets demonstrate that the proposed algorithms achieve identical results to those of their stand-alone counterparts and more than 200% higher accuracy than the simple distributed CPAs without federating learning.

Complex networks in real world are always in the state of evolution and composed of numerous overlapping communities. The discovery of overlapping communities in dynamic networks plays an important role in community detection research. In recent years, methods based on incremental clustering have become increasingly popular owing to their high efficiency. However, few of them can deal with communities that are both overlapping and dynamic. In this article, we propose an incremental clustering algorithm for discovering overlapping communities in dynamic networks. In the initial snapshot of a dynamic network, a degree-based seed selection strategy with concise and effective rules is employed to obtain stable and high-quality overlapping communities, in which the degree of nodes is the number of their neighboring nodes in the subgraph composed of free nodes. In the subsequent snapshots, a four-staged framework based on cascade information diffusion is proposed to update the communities incrementally. In this framework, a cascade information diffusion model is used to simulate the evolution of communities and then the fitness of nodes to the communities they belong to is updated based on node similarity. Experiments conducted on both real-world and artificial datasets show that the proposed algorithm can discover overlapping communities in dynamic networks effectively and outperform to the state-of-art baseline algorithms.

Abstract Community detection on high‐mixed networks has been a challenging problem for complex network researchers. In a Lancichinetti–Fortunato–Radicchi (LFR) network with a mixing parameter mu greater than or equal to 0.5, the quality of the communities partitioned by currently available algorithms will decrease rapidly with increasing mu. To address this issue, we propose a label propagation algorithm on high‐mixed networks, called LPA‐HM, for community detection. In our algorithm, the initial node labels are preprocessed using the number of common neighbors of the nodes, which greatly reduces the initial number of labels and thus improves the quality of the subsequent label propagation process. During the label propagation stage, each node is given the label that is shared by the maximum number of its neighbors. If there are several labels that meet this requirement, the influence of the labels' nodes is calculated, and the label with the maximum total influence is selected as the label of the current node. Early stop conditions based on modularity and run‐to‐run changes in the number of detected communities are incorporated in the algorithm to prevent label overpropagation. The communities that fail to satisfy the definition of weak communities are merged with their most similar neighboring communities. In experiments based on real networks and LFR networks, it is found that the LPA‐HM algorithm is well suited to community detection in a variety of networks. In a high‐mixed LFR network with mu = 0.7, the NMI measure of the LPA‐HM algorithm's community detection performance is still greater than 0.9.

Summary Most of networks in real world obviously present dynamic characteristics over time, and the community structure of adjacent snapshots has a certain degree of instability and temporal smoothing. Traditional Temporal Trade‐off algorithms consider that communities found at time t depend both on past evolutions. Because this kind of algorithms are based on the hypothesis of short‐term smoothness, they can barely find abnormal evolution and group emergence in time. In this paper, a Dynamic Community Detection method based on an improved Evolutionary Matrix (DCDEM) is proposed, and the improved evolutionary matrix combines the community structure detected at the previous time with current network structure to track the evolution. Firstly, the evolutionary matrix transforms original unweighted network into weighted network by incorporating community structure detected at the previous time with current network topology. Secondly, the Overlapping Community Detection based on Edge Density Clustering with New edge Similarity (OCDEDC_NS) algorithm is applied to the evolutionary matrix in order to get edge communities. Thirdly, some small communities are merged to optimize the community structure. Finally, the edge communities are restored to the node overlapping communities. Experiments on both synthetic and real‐world networks demonstrate that the proposed algorithm can detect evolutionary community structure in dynamic networks effectively.

We propose an overlapping community discovery algorithm that combines node influence and [Formula: see text]-connected neighbors for effectively detecting the overlapping community structure of complex networks. On the basis of the node influence and [Formula: see text]-connected neighbors, our method accurately detects the core node community and uses the improved similarity between the node and community to expand the core node community. Accordingly, the discovery and optimization of network overlapping communities are realized. Experiments on artificial and real-world networks demonstrate that our method significantly and consistently outperforms other comparison methods.