Backdoor attacks pose severe security challenges to federated learning systems due to their stealthy nature. Existing detection methods primarily focus on identifying anomalies by analyzing discrepancies in client model updates. However, in federated learning, the non-independent and identically distributed (non-IID) nature of client data leads to inconsistencies among local model updates, which can mask the distinguishing features of backdoor attacks and consequently degrade the performance of detection methods. Unlike benign models, which are trained solely for a single classification task, backdoored models are simultaneously optimized for both the classification (main) task and the backdoor task. Therefore, training the backdoored models can be regarded as a multi-task learning problem. Inspired by information bottleneck theory, we observe that backdoored models exhibit more stable feature representations than benign models when performing the main task. Based on this insight, we propose a novel stability metric that quantitatively captures the disparity in feature map stability between backdoored and benign models. Leveraging this metric, we develop a new backdoor detection framework for federated learning. Our method computes anomaly scores for each client and selectively aggregates models with benign characteristics, effectively defending against backdoor attacks. We validate our approach through extensive experiments on multiple benchmark datasets under non-IID settings. The results demonstrate that our method consistently achieves high detection performance across a range of backdoor scenarios and data heterogeneity levels.

Federated learning is vulnerable to backdoor attacks due to its distributed nature and the inability to access local datasets. Meanwhile, the heterogeneity of distributed data further complicates the detection of such attacks. However, existing defense strategies often overlook the presence of non-stationary objectives and noisy gradients across multiple clients, making it challenging to accurately and efficiently identify malicious participants. To address these challenges, we propose a backdoor defense method for Federated Learning with Adam optimizer and multi-granularity Clustering (FLAC), incorporating both coarse-grained and fine-grained clustering mechanisms to neutralize backdoor attacks. First, the Adam optimizer accelerates the learning process by mitigating the impact of noisy gradients and addressing the non-stationary objectives posed by different clients under attack. Second, a multi-granularity clustering process is considered to differentiate between benign clients and potential attackers. This is followed by an adaptive clipping strategy to further alleviate the influence of malicious attackers. Our theoretical analysis demonstrates the consistent convergence of Adam in a federated backdoor defense environment. Extensive experimental results validate the effectiveness of our defense approach.

Community detection plays an essential role in the domains of social, bioinformatics, and e-commerce. The innovative structural information theory (SInfo, introduced by Li et al.) has achieved excellent performance for network analysis. Nevertheless, similar to traditional network algorithms, the SInfo algorithm will exhaust all system memory resources when processing large-scale networks based on adjacency data structures. Moreover, due to the irregular and sequential characteristics, the SInfo algorithm is challenging to parallelize. In this article, we propose a hybrid sparse data structure and design a low-memory community detection algorithm based on structural information theory (HSSInfo), which shrinks memory requirements and achieves high parallelism. Specifically, we first propose a general quantization method to quantify the information change in community transformation, with which community inner and outer connection complexity can be semantically interpreted. Second, we design a general hybrid sparse structure to store network data among CPU and GPU, which can reduce memory resource consumption for community detection on large-scale networks. Finally, we develop an HSSInfo algorithm based on the quantization method and hybrid sparse structure, in which parallelism intersection and community fusion algorithms are employed to improve parallel scalability. We execute the comparison experiments for HSSInfo and eleven baseline algorithms on nine real-world datasets. Empirically, HSSInfo can achieve orders of magnitude speedups and extend structural information theory to large-scale datasets of billions of edges. Meanwhile, compared with various community detection algorithms, HSSInfo can achieve higher or similar accuracy with up to 19x memory shrinkage ratio.

Collaborative support for a group of members that have common goals has been considered as a significant feature of the collaborative working environment. However, collaborative applications for multi-member generally lag behind in features with single-user applications. As a result, users often continue to use their favorite single-user applications that are less collaborative features. An efficient way is to convert single-user applications into collaborative applications. To our knowledge, there is no general technique available to convert single-user applications into multi-member collaborative applications. In this paper we give a novel approach to convert single-user, legacy CAD applications to collaborative CAD applications. The main characteristic of our approach is that it not only retains the original function of the single-user CAD application, but also supports the cooperative features. And it can improve the constructive efficiency of collaborative CAD applications

By inserting into the mechanism of existing application sharing systems, we have found that almost all the existing application sharing systems cannot both support participants' concurrent operation and provide the characteristics previously seen only in collaboration-aware systems. To overcome their limitations, we propose a novel approach called application cooperating. It can convert single-user, legacy CAD applications into cooperative CAD applications so that group members discuss or modify concurrently the design result generated by single-user CAD applications. The main feature of our approach is: it not only retains the original functions of the cooperated application, but also supports the cooperative work. We first discuss the issues and approaches of our solution. Then an example of an application cooperating system is given.