Backdoor attacks have seriously threatened deep neural networks (DNNs) by embedding concealed vulnerabilities through data poisoning. To counteract these attacks, training benign models from poisoned data garnered considerable interest from researchers. High-performing defenses often rely on additional clean subsets/seeds, which is untenable due to increasing privacy concerns and data scarcity. In the absence of additional clean subsets/seeds, defenders resort to complex feature extraction and analysis, resulting in excessive overhead and compromised performance. To address these challenges, we identify the key lies in sufficient utilization of both the easier-to-obtain target labels and clean hard samples. In this work, we propose a Bi-perspective Splitting Defense (BSD). BSD distinguishes clean samples using both semantic and loss statistics characteristics through open set recognition-based splitting (OSS) and altruistic model-based data splitting (ALS) respectively. Through extensive experiments on benchmark datasets and against representative attacks, we empirically demonstrate that BSD surpasses existing defenses by over 20% in average Defense Effectiveness Rating (DER), achieving clean data-free backdoor security.

Dynamic Dependence Network (DDN) inference is crucial for understanding evolving relationships in multimodal time series web data, with broad applications in fields like medical and financial network analysis. The inherent dynamic nature, temporal continuity, and heterogeneous data sources in multimodal time series data pose three fundamental challenges: computational efficiency, prediction stability and robustness, and modality quality disparity. Previous methods, generally lacking utilization of multiple modalities, either struggle with computational efficiency due to the time-intensive manual hyperparameter tuning, or compromise prediction stability and robustness by neglecting temporal coherence. To address these challenges, we propose a Normalized mutual information-driven Tuning-free Dynamic Dependence Network inference method for multimodal data, namely NoTeNet. NoTeNet provides a promising paradigm that can integrate two different data modalities to enhance prediction accuracy. It uses normalized mutual information transforms noisy auxiliary data into relationship matrices and employs a kernel function for smooth temporal estimation. Additionally, NoTeNet significantly reduces the need for manual hyperparameter adjustments, offering a tuning-free approach with theoretical guarantees. On various synthetic datasets and real-world data, NoTeNet demonstrates superior prediction accuracy and efficiency without the need for hyperparameter tuning, making it potential for a wide range of web data applications.

ABSTRACT The differential evolution algorithm, as a simple yet effective random search algorithm, often faces challenges in terms of rapid convergence and a sharp decline in population diversity during the evolutionary process. To address this issue, an improved differential evolution algorithm, namely the multi‐population collaboration improved differential evolution (MPC‐DE) algorithm, is introduced in this article. The algorithm proposes a multi‐population collaboration mechanism and a two‐stage mutation operator. Through the multi‐population collaboration mechanism, the diversity of individuals involved in mutation is effectively controlled, enhancing the algorithm's global search capability. The two‐stage mutation operator efficiently balances the requirements of the exploration and exploitation stages. Additionally, a perturbation operator is introduced to enhance the algorithm's ability to escape local optima and improve stability. By conducting comprehensive comparisons with 15 well‐known optimization algorithms on CEC2005 and CEC2017 test functions, MPC‐DE is thoroughly evaluated in terms of solution accuracy, convergence, stability, and scalability. Furthermore, validation on 57 real‐world engineering optimization problems in CEC2020 demonstrates the robustness of the MPC‐DE. Experimental results reveal that, compared to other algorithms, MPC‐DE exhibits superior convergence accuracy and robustness in both constrained and unconstrained optimization problems. These research findings provide strong support for the widespread applicability of multi‐population collaboration in differential evolution algorithms for addressing practical engineering problems.

Precision matrix estimation is a ubiquitous task featuring numerous applications such as rare disease diagnosis and neural connectivity exploration. However, this task becomes challenging in small sample settings, where the number of samples is significantly less than the number of dimensions, leading to unreliable estimates. Previous approaches either fail to perform well in small sample settings or suffer from inefficient estimation processes, even when incorporating meta-learning techniques. To this end, we propose a novel approach FasMe for Fast and Sample-efficient Meta Precision Matrix Learning, which first extracts meta-knowledge through a multi-task learning diagram. Then, meta-knowledge constraints are applied using a maximum determinant matrix completion algorithm for the novel task. As a result, we reduce the sample size requirements to $O(\log p/K)$ per meta-training task and $O(\log\vert \mathcal{G}\vert)$ for the meta-testing task. Moreover, the hereby proposed model only needs $O(p \log\epsilon^{-1})$ time and $O(p)$ memory for converging to an $\epsilon$-accurate solution. On multiple synthetic and biomedical datasets, FasMe is at least ten times faster than the four baselines while promoting prediction accuracy in small sample settings.

Graph knowledge discovery from graph-structured data is a fascinating data mining topic in various domains, especially in the Internet of Things, where inferring the graph structure from such informative data can benefit many downstream tasks. Deep neural networks are typically used to perform such predictions, but they produce unreliable results without sufficient high-quality data. Therefore, researchers introduce lightweight statistical precision matrix learning to infer the graph structure in many IoT scenarios with limited communication and resolution of sensors. However, these methods still suffer from low-resolution data or the omission of hidden information in time-series data. To address the challenges, we propose a novel approach for Energy-efficient Dynamic Sparse Graph Structure Estimation with one-bit data, EDGE. Our method proposes a novel estimator to estimate the covariance matrix from one-bit data, and then utilize the covariance matrices to capture the dynamic structure. We theoretically demonstrate the effectiveness of the estimators by deriving two non-asymptotic estimation error bounds for the estimated covariance matrix and precision matrix, respectively. The theoretical results show that our method can achieve a consistent result of the precision matrix at the rate O(log p/n). On multiple synthetic and real-world datasets, the experimental results demonstrate that our proposed estimator is able to obtain a relatively high detection rate using one-bit data, which exceeds the baseline by 35%, and identify potentially perturbed nodes in real-time dynamic network inference.