检索结果-内蒙古大学图书馆

PrivBox: Privacy-Preserving Deep Packet Inspection with Dual Double-masking Obfuscated Rule Generation

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Wu, Pengfei Ning, Jianting Huang, Xinyi Chen, Rongmao Zhang, Kai Liang, Kaitai Wuhan University School of Cyber Science and Engineering Wuhan China Singapore Management University School of Computing and Information Systems Singapore City University of Macau Faculty of Data Science Macau China Fujian Normal University College of Computer and Cyber Security Fuzhou China Jinan University College of Cyber Security Guangzhou China National University of Defense Technology College of Computer Changsha China Shanghai University of Electric Power College of Computer Science and Technology Shanghai China Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Netherlands

Many network middleboxes have been deployed to perform deep packet inspection (DPI) over packet payloads. However, such middleboxes cannot accomplish their tasks when the traffic is encrypted. BlindBox (SIGCOMM 2015) provided the first solution for performing DPI over encrypted traffic. To improve its efficiency, a later proposal PrivDPI (CCS 2019) introduced a practical technique to generate encrypted rules. However, a recent proposal P2DPI (ASIACCS 2021) showed that the rule generator in PrivDPI can comprise the user's privacy. In this paper, we present a new attack on P2DPI and show that the privacy of its endpoints can still be compromised by the rule generator. We comprehensively analyze the vulnerability of prior studies and present PrivBox, a new DPI system that achieves the same privacy guarantee as BlindBox while maintaining practical efficiency. This is based on a new technique called dual double-masking obfuscated rule generation. For a ruleset of 3,000, PrivBox achieves connection establishment time on the endpoint side comparable to PrivDPI and supports up to 4,672 token encryptions per second, which is sufficient for a number of real-world applications. Overall, our experiment demonstrates that PrivBox is practical and well-suited for short, frequently established sessions, especially when token repeating is common. ©2004-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

MAGIC: detecting advanced persistent threats via masked graph representation learning 24

MAGIC: detecting advanced persistent threats via masked grap...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Zian Jia Yun Xiong Yuhong Nan Yao Zhang Jinjing Zhao Mi Wen Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Software Engineering Sun Yat-sen University China National Key Laboratory of Science and Technology on Information System Security China Shanghai University of Electric Power China

ISBN: (纸本)9781939133441

Advance Persistent Threats (APTs), adopted by most delicate attackers, are becoming increasing common and pose great threat to various enterprises and institutions. Data provenance analysis on provenance graphs has emerged as a common approach in APT detection. However, previous works have exhibited several shortcomings: (1) requiring attack-containing data and a priori knowledge of APTs, (2) failing in extracting the rich contextual information buried within provenance graphs and (3) becoming impracticable due to their prohibitive computation overhead and memory *** this paper, we introduce MAGIC, a novel and flexible self-supervised APT detection approach capable of performing multi-granularity detection under different level of supervision. MAGIC leverages masked graph representation learning to model benign system entities and behaviors, performing efficient deep feature extraction and structure abstraction on provenance graphs. By ferreting out anomalous system behaviors via outlier detection methods, MAGIC is able to perform both system entity level and batched log level APT detection. MAGIC is specially designed to handle concept drift with a model adaption mechanism and successfully applies to universal conditions and detection scenarios. We evaluate MAGIC on three widely-used datasets, including both real-world and simulated attacks. Evaluation results indicate that MAGIC achieves promising detection results in all scenarios and shows enormous advantage over state-of-the-art APT detection approaches in performance overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Air-Space-Ground Synergistic Observations for Rapid Post-Seismic Disaster Assessment of 2025 Ms6.8 Xigaze Earthquake,Xizang

引用

Journal of Earth science 2025年

作者： Jie Dou Ke Xing Lizhe Wang Haixiang Guo Dun Wang Yigui Peng Xinjian Xiang Dunzhu Ciren Songcheng Zhang Lele Zhang Bo Peng Badong National Observation and Research Station of Geohazards China University of Geosciences National Engineering Research Center of Geographic Information System China University of Geosciences Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of Geosciences School of Computer Science China University of Geosciences School of Economics and Management China University of Geosciences(Wuhan) School of Earth Sciences China University of Geosciences Xizang Autonomous Region Water Conservancy and Electric Power Planning Survey and Design Institute

On January 7,2025,an Ms6.8 earthquake struck Dingri County,Xigaze City,Xizang Autonomous *** epicenter,located near the Shenzha-Dingjie fault zone at the boundary between the Qinghai-Xizang Plateau and the Indian Plate,marked the largest earthquake in the region in recent *** Shenzha-Dingjie fault zone,situated at the boundary between the Qinghai-Xizang Plateau and the Indian Plate,is a key tectonic feature in the India-Eurasia collision process,characterized by active structural deformation manifested as both thrust and strike-slip *** study analyzed the disaster characteristics induced by the earthquake using differential synthetic aperture radar interferometry (D-InSAR) to process Sentinel-1 satellite data and derive pre-and post-earthquake surface deformation ***,high-resolution optical remote sensing data,UAV imagery,and airborne Li DAR data were employed to analyze the spatial distribution of the surface rupture zone,with field investigations validating the *** results include:(1) Potential landslide hazard points identified through optical image interpretation did not show secondary landslide activity upon field verification;(2) D-InSAR revealed the co-seismic surface deformation pattern,providing detailed deformation information for the Dingri region;(3) Integration of LiDAR and optical imagery further refined and validated surface rupture characteristics identified by optical-InSAR,indicating a predominantly north-south rupture ***,surface rupture features extending in a near east-west direction were observed on the southeast side of the epicenter,accompanied by some infrastructure damage;(4) Surface rupture was most severe in high-intensity seismic areas near the epicenter,with the maximum surface displacement approximately 28 km from the *** earthquake-induced surface deformation zone spanned approximately 6 km by 46 km,with deformation concentrated primarily on the western side

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visualizing the Local Atomic Environment Features of Machine Learning Interatomic Potential

arXiv

引用

arXiv 2025年

作者： Shao, Xuqiang Zhang, Yuqi Zhang, Di Gao, Tianxiang Liu, Xinyuan Gan, Zhiran Meng, Fanshun Li, Hao Yang, Weijie School of Control and Computer Engineering North China Electric Power University Baoding071003 China Tohoku University Sendai980-8577 Japan Department of Power Engineering School of Energy and Power Engineering North China Electric Power University Hebei Baoding071003 China School of Science Liaoning University of Technology Jinzhou12100l China

This paper addresses the challenges of creating efficient and high-quality datasets for machine learning potential functions. We present a novel approach, termed DV-LAE (Difference Vectors based on Local Atomic Environments), which utilizes the properties of atomic local environments and employs histogram statistics to generate difference vectors. This technique facilitates dataset screening and optimization, effectively minimizing redundancy while maintaining data diversity. We have validated the optimized datasets in high-temperature and high-pressure hydrogen systems as well as the α-Fe/H binary system, demonstrating a significant reduction in computational resource usage without compromising prediction accuracy. Additionally, our method has revealed new structures that emerge during simulations but were underrepresented in the initial training datasets. The redundancy in the datasets and the distribution of these new structures can be visually analyzed through the visualization of difference vectors. This approach enhances our understanding of the characteristics of these newly formed structures and their impact on physical processes. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

CONFORMAL UNCERTAINTY INDICATOR FOR CONTINUAL TEST-TIME ADAPTATION

arXiv

引用

arXiv 2025年

作者： Lyu, Fan Zhao, Hanyu Shi, Ziqi Liu, Ye Hu, Fuyuan Zhang, Zhang Wang, Liang New Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China China Nuclear Power Engineering Co. LTD China College of Intelligence and Computing Tianjin University China School of Computer Science & Engineering LinYi University China School of Electric & Information Engineering Suzhou University of Science and Technology China

Continual Test-Time Adaptation (CTTA) aims to adapt models to sequentially changing domains during testing, relying on pseudo-labels for self-adaptation. However, incorrect pseudo-labels can accumulate, leading to performance degradation. To address this, we propose a Conformal Uncertainty Indicator (CUI) for CTTA, leveraging Conformal Prediction (CP) to generate prediction sets that include the true label with a specified coverage probability. Since domain shifts can lower the coverage than expected, making CP unreliable, we dynamically compensate for the coverage by measuring both domain and data differences. Reliable pseudo-labels from CP are then selectively utilized to enhance adaptation. Experiments confirm that CUI effectively estimates uncertainty and improves adaptation performance across various existing CTTA methods. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Universal Catalyst Design Framework for Electrochemical Hydrogen Peroxide Synthesis Facilitated by Local Atomic Environment Descriptors

arXiv

引用

arXiv 2025年

作者： Liu, Zhijian Liu, Yan Zhang, Bingqian Zhang, Yuqi Gao, Tianxiang Li, Mingzhe Jia, Xue Zhang, Di Liu, Heng Shao, Xuqiang Wei, Li Li, Hao Yang, Weijie School of Energy and Power Engineering North China Electric Power University Baoding071003 China Department of Computer Science North China Electric Power University Baoding071003 China Tohoku University Sendai980-8577 Japan School of Chemical and Biomolecule Engineering The University of Sydney SydneyNSW Australia

Developing a universal and precise design framework is crucial to search high-performance catalysts, but it remains a giant challenge due to the diverse structures and sites across various types of catalysts. To address this challenge, herein, we developed a novel framework by the refined local atomic environment descriptors (i.e., weighted Atomic Center Symmetry Function, wACSF) combined with machine learning (ML), microkinetic modeling, and computational high-throughput screening. This framework is successfully integrated into the Digital Catalysis Database (DigCat), enabling efficient screening for 2e- water oxidation reaction (2e- WOR) catalysts across four material categories (i.e., metal alloys, metal oxides and perovskites, and single-atom catalysts) within a ML model. The proposed wACSF descriptors integrating both geometric and chemical features are proven effective in predicting the adsorption free energies with ML. Excitingly, based on the wACSF descriptors, the ML models accurately predict the adsorption free energies of hydroxyl (ΔGOH*) and oxygen (ΔGO*) for such a wide range of catalysts, achieving R2values of 0.84 and 0.91, respectively. Through density functional theory calculations and microkinetic modeling, a universal 2e- WOR microkinetic volcano model was derived with excellent agreement with experimental observations reported to date, which was further used to rapidly screen high-performance catalysts with the input of ML-predicted ΔGOH*. Most importantly, this universal framework can significantly improve the efficiency of catalyst design by considering multiple types of materials at the same time, which can dramatically accelerate the screening of high-performance catalysts. This framework is general and proven effective for predicting ΔGOH* and ΔGO*, which is expected to be also applicable for the materials design of various catalysis. © 2025, CC BY.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Durable carrier-free catalytic combustion H2 sensor based on PdPt alloy nanoparticles

引用

International Journal of Hydrogen Energy 2025年 138卷 28-35页

作者： Bao, Keda Qiu, Siyi Wang, Wentian Yang, Chao Wang, Wei Wang, Xiaoli Wang, Qijun Yin, Jiawen Jin, Qinghui Jian, Jiawen Zou, Jie School of Electrical Engineering and Computer Science Ningbo University Ningbo315000 China Hangzhou International Innovation Institute Beihang University Hangzhou311115 China Xiamen Hongfa Electric Power Controls Co. Ltd. Xiamen361000 China

The new palladium nanoparticles (Pd NPs) based carrier-free catalytic combustion hydrogen (H2) sensor presents a promising potential for H2 energy vehicle due to excellent vibration and low power consumption. However, the sintering of the Pd NPs at elevated temperatures decreases the sensitivity, limiting the applications of these sensors. To enhance the durability of Pd NPs based carrier-free catalytic combustion H2 sensor, palladium-platinum alloy nanoparticles (PdPt NPs) was fabricated on the filament by a co-electrodeposition method. The impact of morphology and composition of PdPt NPs on the sensing performance was systematically investigated. The results indicated that Pt atoms in the alloy can restrict the mobility of Pd atoms, which may reduce the sintering between particles at elevated temperatures. Compared to a pure Pd NPs H2 sensor, the PdPt NPs H2 sensor demonstrated superior sensitivity and linearity and their low power consumption and durability were significantly improved. © 2025 Hydrogen Energy Publications LLC

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

A New Denoising Method for Ship-Radiated Noise Based on Complete Ensemble Empirical Mode Decomposition

A New Denoising Method for Ship-Radiated Noise Based on Comp...

引用

IEEE Information Technology and Mechatronics engineering Conference (ITOEC)

作者： Zewen Zhuang Haoyu Chen Jianxun Tang Mingsong Chen Xingjian Hezhou School of Information and Communication Guilin University of Electronic Technology Guilin China School of Electric Power Engineering Guangxi Electrical Polytechnic Institute Nanning China School of Ocean Engineering Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331529482

ISBN: (纸本)9798331529499

Noise reduction lays a foundation for feature extraction and identification of ship-radiated noise. To improve the signal-to-noise ratio (SNR) of ship-radiated noise, a new denoising scheme is proposed in this paper, based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and improved permutation entropy (IPE). The proposed approach initiates with the decomposition of ship-generated acoustic signals into multiple intrinsic mode functions (IMFs) through the CEEMDAN technique. Subsequently, these IMF components are categorized into three distinct groups -pure noise components, noise-biased components, and signal-dominant components - based on their respective IPE metrics. The processing strategy involves discarding the pure noise IMFs while applying least mean square adaptive filtering (LMSAF) to refine the noise-biased components. The final denoised output is reconstructed by integrating the processed noise-dominant IMFs with the unaltered signal-dominant IMFs. Experimental validation through both simulated and real-world acoustic datasets demonstrates the superior performance of this approach. Comparative analysis reveals that the proposed technique outperforms conventional methods, providing a more reliable preprocessing solution for underwater acoustic signal analysis and subsequent interpretation tasks.

关键词： Empirical mode decomposition Filtering Noise reduction Entropy Underwater acoustics Signal analysis Signal resolution Mutual information Signal integrity Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Trust-Based Personalized Differential Privacy Guarantees for Online Social Networks

引用

IEEE Transactions on Network and Service Management 2025年

作者： Chen, Jiajun Hu, Chunqiang Sheng, Weihong Li, Ruinian Zhao, Ruifeng Yu, Jiguo Chongqing University College of Computer Science Chongqing401331 China Chongqing University School of Big Data and Software Engineering Chongqing401331 China Bowling Green State University Computer Science Department United States Electric Power Dispatching and Control Center of Guangdong Power Grid Co. Ltd Guangzhou China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu611731 China Qilu University of Technology Big Data Institute Jinan250353 China

Online social networks have emerged as a significant data source, but the extensive collection and utilization of personal information have given rise to profound concerns regarding privacy. From a legislative and policy perspective, and in alignment with the concept of privacy as control, users have the right to control their personal privacy information. However, users often encounter challenges in terms of understanding and effectively managing their privacy settings to align with their specific privacy requirements. To address this issue, in this paper, we incorporate the concept of trust and propose a trust-based personalized differential privacy model for online social networks, denoted as TPDP, which relies on a trusted central server to facilitate its operation. Specifically, when a user requests access to another user's personal information, the TPDP mechanism provides a privacy response, where the privacy level is determined based on the direct and indirect trust values among users, calculated automatically by the trusted central server. Furthermore, the proposed TPDP model offers user-to-user personalized differential privacy protection from the perspectives of network structures, trust-related factors, and trust propagation patterns. Finally, we validate the model's feasibility and assess the privacy-utility trade-off, as well as its robustness against attacks, through theoretical analysis and performance evaluation. © 2004-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Applying auxiliary supervised depthassisted transformer and cross modal attention fusion in monocular 3D object detection

引用

PeerJ computer science 2025年 11卷 e2656-e2656页

作者： Wang, Zhijian Liu, Jie Sun, Yixiao Zhou, Xiang Sun, Boyan Kong, Dehong Xu, Jay Yue, Xiaoping Zhang, Wenyu School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan China Anshan Power Supply Company Liaoning Electric Power Limited Company of State Grid Liaoning Anshan China Inner Mongolia Electronic Information Vocational Technical College Neimenggu Huhehaote China

Monocular 3D object detection is the most widely applied and challenging solution for autonomous driving, due to 2D images lacking 3D information. Existing methods are limited by inaccurate depth estimations by inequivalent supervised targets. The use of both depth and visual features also faces problems of heterogeneous fusion. In this article, we propose Depth Detection Transformer (Depth-DETR), applying auxiliary supervised depth-assisted transformer and cross modal attention fusion in monocular 3D object detection. Depth-DETR introduces two additional depth encoders besides the visual encoder. Two depth encoders are supervised by ground truth depth and bounding box respectively, working independently to complement each other’s limitations and predicting more accurate target distances. Furthermore, Depth-DETR employs cross modal attention mechanisms to effectively fuse three different features. A parallel structure of two cross modal transformer is applied to fuse two depth features with visual features. Avoiding early fusion between two depth features enhances the final fused feature for better feature representations. Through multiple experimental validations, the Depth-DETR model has achieved highly competitive results in the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset, with an AP score of 17.49, representing its outstanding performance in 3D object detection. © 2025 Wang et al.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：