检索结果-内蒙古大学图书馆

Evading Detection Actively: Toward Anti-Forensics Against Forgery Localization

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 2025年第2期22卷 852-869页

作者： Zhuo, Long Luo, Shenghai Tan, Shunquan Chen, Han Li, Bin Huang, Jiwu Shenzhen MSU BIT Univ Guangdong Lab Machine Percept & Intelligent Comp Fac Engn Shenzhen 518116 Peoples R China Shenzhen Key Lab Media Secur Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Guangdong Peoples R China

Anti-forensics seeks to eliminate or conceal traces of tampering artifacts. Typically, anti-forensic methods are designed to deceive binary detectors and persuade them to misjudge the authenticity of an image. However, to the best of our knowledge, no attempts have been made to deceive forgery detectors at the pixel level and mis-locate forged regions. Traditional adversarial attack methods cannot be directly used against forgery localization due to the following defects: 1) they tend to just naively induce the target forensic models to flip their pixel-level pristine or forged decisions;2) their anti-forensics performance tends to be severely degraded when faced with the unseen forensic models;3) they lose validity once the target forensic models are retrained with the anti-forensics images generated by them. To tackle the three defects, we propose SEAR (Self-supErvised Anti-foRensics), a novel self-supervised and adversarial training algorithm that effectively trains deep-learning anti-forensic models against forgery localization. SEAR sets a pretext task to reconstruct perturbation for self-supervised learning. In adversarial training, SEAR employs a forgery localization model as a supervisor to explore tampering features and constructs a deep-learning concealer to erase corresponding traces. We have conducted large-scale experiments across diverse datasets. The experimental results demonstrate that, through the combination of self-supervised learning and adversarial learning, SEAR successfully deceives the state-of-the-art forgery localization methods, as well as tackle the three defects regarding traditional adversarial attack methods mentioned above.

关键词： Location awareness Training Forensics Perturbation methods computational modeling Self-supervised learning Detectors Forgery Adversarial machine learning Robustness Anti-forensics concealer supervisor self-supervised training adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Distilling Wisdom: A Review on Optimizing Learning From Massive Language Models

引用

IEEE ACCESS 2025年 13卷 56296-56325页

作者： Zhang, Dingzong Listiyani, Devi Singh, Priyanka Mohanty, Manoranjan Univ Queensland Sch Elect Engn & Comp Sci Brisbane Qld 4072 Australia Carnegie Mellon Univ Qatar Sch Elect Engn & Comp Sci Ar Rayyan Qatar

In the era of Large Language Models (LLMs), Knowledge Distillation (KD) enables the transfer of capabilities from proprietary LLMs to open-source models. This survey provides a detailed discussion of the basic principles, algorithms, and implementation methods of knowledge distillation. It explores KD's impact on LLMs, emphasizing its utility in model compression, performance enhancement, and self-improvement. Through the analysis of practical examples such as DistilBERT, TinyBERT, and MobileBERT, the paper demonstrates how knowledge distillation can markedly enhance the efficiency and applicability of large language models in real-world scenarios. The discussion encompasses the varied applications of KD across multiple domains, including industrial systems, embedded systems, Natural Language Processing (NLP), multi-modal processing, and vertical domains, such as medicine, law, science, finance, and materials science. This survey outlines current KD methodologies and future research directions, highlighting its role in advancing AI technologies and fostering innovation across different sectors.

关键词： Transformers computational modeling Surveys Natural language processing Predictive models Artificial intelligence Technological innovation Encoding Context modeling Artificial intelligence (AI) large language model (LLM) knowledge distillation (KD) optimization optimization

来源：评论

学校读者我要写书评

暂无评论

ReferSAM: Unleashing Segment Anything Model for Referring Image Segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第5期35卷 4910-4922页

作者： Liu, Sun-Ao Xie, Hongtao Ge, Jiannan Zhang, Yongdong Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230022 Peoples R China

The Segment Anything Model (SAM) has demonstrated remarkable capability as a general segmentation model given visual prompts such as points or boxes. While SAM is conceptually compatible with text prompts, it merely employs linguistic features from vision-language models as prompt embeddings and lacks fine-grained cross-modal interaction. This deficiency limits its application in referring image segmentation (RIS), where the targets are specified by free-form natural language expressions. In this paper, we introduce ReferSAM, a novel SAM-based framework that enhances cross-modal interaction and reformulates prompt encoding, thereby unleashing SAM's segmentation capability for RIS. Specifically, ReferSAM incorporates the Vision-Language Interactor (VLI) to integrate linguistic features with visual features during the image encoding stage of SAM. This interactor introduces fine-grained alignment between linguistic features and multi-scale visual representations without altering the architecture of pre-trained models. Additionally, we present the Vision-Language Prompter (VLP) to generate dense and sparse prompt embeddings by aggregating the aligned linguistic and visual features. Consequently, the generated embeddings sufficiently prompt SAM's mask decoder to provide precise segmentation results. Extensive experiments on five public benchmarks demonstrate that ReferSAM achieves state-of-the-art performance on both classic and generalized RIS tasks. The code and models are available at https://***/lsa1997/ReferSAM.

关键词： Visualization Image segmentation Decoding Linguistics Feature extraction computational modeling Vectors Transformers Image coding Circuits and systems Referring image segmentation segment anything vision-language interactor prompt learning

来源：评论

学校读者我要写书评

暂无评论

WavFace: A Multimodal Transformer-Based Model for Depression Screening

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2025年第5期29卷 3632-3641页

作者： Flores, Ricardo Tlachac, M. L. Shrestha, Avantika Rundensteiner, Elke A. Univ Concepcion Dept Comp Sci n Concepci&x00F3 Concepcion Chile Worcester Polytech Inst Dept Data Sci Worcester MA 01609 USA Bryant Univ Dept Informat Syst & Analyt Smithfield RI 01609 USA Bryant Univ Ctr Hlth & Behav Sci Smithfield RI 01609 USA

Depression, a prevalent mental health disorder with severe health and economic consequences, can be costly and difficult to detect. To alleviate this burden, recent research has been exploring the depression screening capabilities of deep learning (DL) models trained on videos of clinical interviews conducted by a virtual agent. Such DL models need to consider the challenges of modality representation, alignment, and fusion as well as small sample sizes. To address them, we propose WavFace, a multimodal deep learning model that inputs audio and temporal facial features. WavFace adds an encoder-transformer layer over pre-trained models to improve the unimodal representation. It also applies an explicit alignment method for both modalities and then uses sequential and spatial self-attention over the alignment. Finally, WavFace fuses the sequential and spatial self-attentions among the two modality embeddings, inspired by how mental health professionals simultaneously observe visual and vocal presentation during clinical interviews. By leveraging sequential and spatial self-attention, WavFace outperforms pre-trained unimodal and multimodal models from the literature. With a single interview question, WaveFace screened for depression with a balanced accuracy of 0.81. This presents a valuable modeling approach for audio-visual mental health screening.

关键词： Depression Interviews Deep learning Facial features Videos Transformers computational modeling Telemedicine Mental health Bidirectional long short term memory Digital health digital biomarkers time series classification transfer Learning alignment fusion

来源：评论

学校读者我要写书评

暂无评论

RCLT-Net: An Indoor Panoramic Room Layout Estimation Framework Based on Consecutive Dilated Convolutions and Transformer

引用

IEEE ACCESS 2025年 13卷 45923-45935页

作者： Sun, Qiucheng Deng, Zhengkai Zhu, Jinlong Changchun Normal Univ Inst Comp Sci & Technol Changchun 130032 Peoples R China

Current mainstream models for indoor panoramic room layout depth estimation primarily utilize deep residual networks and various Transformer-based modifications to reconstruct room boundaries from 2D images. However, these methods often encounter challenges such as limited receptive fields, insufficient multi-scale feature interaction and integration capabilities, and blurred boundary estimations in complex scenes. To overcome these challenges, we propose ResCDC-Net, a novel feature extraction model that expands the receptive field by incorporating continuous dilated convolutions within convolutional layers and applying varying dilation rates in residual blocks. This design enhances the perception of fine-grained multi-scale features. Additionally, we introduce the Local-Global Feature Interaction Shifting Window Transformer, which significantly improves the Transformer model's ability to extract features by fostering robust interactions between local and global features, enabling more flexible and efficient feature representation. Furthermore, we employ a triplet loss function based on positive and negative anchor points to ensure clear boundary distinctions in complex object boundary regions. Extensive experiments validate that our proposed RCLT-Net surpasses SoTA models in depth estimation accuracy and demonstrates exceptional performance across multiple challenging public datasets.

关键词： Layout Depth measurement Feature extraction Transformers Estimation Accuracy Solid modeling computational modeling Training Sun Depth estimation panoramic room layout continuous dilated convolution local-global feature interaction

来源：评论

学校读者我要写书评

暂无评论

Detection of Potential Breeding Sites Based on AAV Remote Sensing Imagery and MultiDCCSP-YOLO Network

引用

IEEE ACCESS 2025年 13卷 52972-52982页

作者： Gao, Zichen Liu, Qinmei Zhou, Yibin Liu, Qing Ma, Zu Ding, Huaiyue Ren, Bin Xiang, Deliang Zhang, Hengduan State Key Lab Pathogen & Biosecur Beijing 100071 Peoples R China Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China Zhejiang Prov Ctr Dis Control & Prevent Hangzhou 310057 Peoples R China Shanghai Minhang Ctr Dis Control & Prevent Shanghai 201101 Peoples R China Chinese Peoples Liberat Army Gen Hosp Senior Dept Neurosurg Med Ctr 1 Beijing 100071 Peoples R China

Detection and control of potential breeding sites (PBS) for Aedes albopictus are considered among the most effective methods for managing mosquito-borne diseases. Due to the high adaptability and rapid reproduction of mosquitoes, PBS are widely distributed. Traditional manual investigation methods are inefficient and would increase the risk of exposure. Autonomous Aerial Vehicle (AAV) remote sensing technology, with its speed and broad coverage, can capture large-scale images quickly. However, current PBS detection methods primarily focus on the detection of large, regular containers. To address the issue for detecting diverse PBS in complex environments, we propose a method called MultiDCCSP-YOLO. This approach integrates several modules to improve the PBS detection accuracy from AAV remote sensing images with challenging backgrounds. We introduce the Multi-DC Block and use it to build the CSPDCStage module. This module captures multi-scale features while reducing computational demands without compromising the detection accuracy. The FasterELAN module minimizes overfitting risks and enhances the detection of PBS targets with limited-sample classes. Additionally, we incorporate the Adaptive Threshold Focal Loss (ATFL) function to emphasize small, hard-to-detect targets, thereby improving multi-scale PBS detection performance. The MultiDCCSP-YOLO method enables efficient and accurate PBS detection in complex environments, facilitating large-scale monitoring efforts.

关键词： Remote sensing Autonomous aerial vehicles Convolution Feature extraction Adaptation models computational modeling Accuracy Neck Computer architecture Training Potential breeding sites Aedes albopictus autonomous aerial vehicle (AAV) target detection remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Time-Optimal Motion Planning and Anti-Sloshing Control for a Container Under Disturbances

引用

IEEE ACCESS 2025年 13卷 26707-26726页

作者： Viet, Khanh Nguyen Thi, Hue Luu Duc, Thanh Cao Danh, Huy Nguyen Vu, Minh Nhat Nguyen, Tung Lam Hanoi Univ Sci & Technol Hanoi 100000 Vietnam Elect Power Univ Hanoi 100006 Vietnam Vietnam Maritime Univ Haiphong 180000 Vietnam Tech Univ Wien TU Wien A-1040 Vienna Austria Austrian Inst Technol AIT A-1210 Vienna Austria

Sloshing is the term for the liquid's internal movement, which is often undesirable in technological processes. This paper aims to provide a solution for suppressing sloshing liquid in a moving cylindrical container. To prevent the negative impact of the sloshing problem, our approach is a combination of generating a desired path, robust control, and output constraints. To begin with, this research introduces a discrete model derived from a nonlinear equivalent mass-spring-damper system. Subsequently, after establishing the flatness of the approximate nonlinear model, we introduce rest-to-rest and time-optimal trajectory planning. We overcome the unmeasurable state variable and disturbance with the Linear Extended State Observer (LESO) algorithm. In addition, to address the challenge of tracking the orbital path, we suggest a control technique Terminal Sliding Mode Control (TSMC), which is well-known for its fast convergence while ensuring global stability. Moreover, to meet the constraints of a practical system, the control barrier function is applied. Lastly, the effectiveness of this control methodology is validated by comprehensive numerical simulations.

关键词： Liquids Containers Mathematical models Trajectory Uncertainty Safety Numerical stability computational modeling State estimation Oscillators Anti-sloshing control control barrier function flatness-based trajectory planning terminal sliding mode control base LESO

来源：评论

学校读者我要写书评

暂无评论

Humas: A Heterogeneity- and Upgrade-Aware Microservice Auto-Scaling Framework in Large-Scale Data Centers

引用

IEEE TRANSACTIONS ON COMPUTERS 2025年第3期74卷 968-982页

作者： Hua, Qin Yang, Dingyu Qian, Shiyou Cao, Jian Xue, Guangtao Li, Minglu Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China Zhejiang Univ State Key Lab Blockchain & Data Secur Hangzhou 310007 Peoples R China Zhejiang Normal Univ Sch Comp Sci & Technol Jinhua 321004 Peoples R China

An effective auto-scaling framework is essential for microservices to ensure performance stability and resource efficiency under dynamic workloads. As revealed by many prior studies, the key to efficient auto-scaling lies in accurately learning performance patterns, i.e., the relationship between performance metrics and workloads in data-driven schemes. However, we notice that there are two significant challenges in characterizing performance patterns for large-scale microservices. Firstly, diverse microservices demonstrate varying sensitivities to heterogeneous machines, causing difficulty in quantifying the performance difference in a fixed manner. Secondly, frequent version upgrades of microservices result in uncertain changes in performance patterns, known as pattern drifts, leading to imprecise resource capacity estimation issues. To address these challenges, we propose Humas, a heterogeneity- and upgrade-aware auto-scaling framework for large-scale microservices. Firstly, Humas quantifies the difference in resource efficiency among heterogeneous machines for various microservices online and normalizes their resources in standard units. Additionally, Humas develops a least-squares density-difference (LSDD) based algorithm to identify pattern drifts caused by upgrades. Lastly, Humas generates capacity adjustment plans for microservices based on the latest performance patterns and predicted workloads. The experiment results conducted on 50 real microservices with over 11,000 containers demonstrate that Humas improves resource efficiency and performance stability by approximately 30.4% and 48.0%, respectively, compared to state-of-the-art approaches.

关键词： Microservice architectures Central Processing Unit Hardware Containers Data centers Computers computational modeling Load modeling Data models Capacity planning Cloud computing microservices data center auto-scaling capacity planning hardware heterogeneity micro service upgrade

来源：评论

学校读者我要写书评

暂无评论

AsyncFedGAN: An Efficient and Staleness-Aware Asynchronous Federated Learning Framework for Generative Adversarial Networks

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2025年第3期36卷 553-569页

作者： Manu, Daniel Alazzwi, Abee Yao, Jingjing Lin, Youzuo Sun, Xiang Univ New Mexico Dept Elect & Comp Engn SECNet Labs Albuquerque NM 87131 USA Texas Tech Univ Dept Comp Sci Lubbock TX 79409 USA Univ North Carolina Chapel Hill Sch Data Sci & Soc Chapel Hill NC 27599 USA

Generative Adversarial Networks (GANs) are deep learning models that learn and generate new samples similar to existing ones. Traditionally, GANs are trained in centralized data centers, raising data privacy concerns due to the need for clients to upload their data. To address this, Federated Learning (FL) integrates with GANs, allowing collaborative training without sharing local data. However, this integration is complex because GANs involve two interdependent models-the generator and the discriminator-while FL typically handles a single model over distributed datasets. In this article, we propose a novel asynchronous FL framework for GANs, called AsyncFedGAN, designed to efficiently and distributively train both models tailored for molecule generation. AsyncFedGAN addresses the challenges of training interactive models, resolves the straggler issue in synchronous FL, reduces model staleness in asynchronous FL, and lowers client energy consumption. Our extensive simulations for molecular discovery show that AsyncFedGAN achieves convergence with proper settings, outperforms baseline methods, and balances model performance with client energy usage.

关键词： Training computational modeling Generative adversarial networks Generators Data models Convergence Load modeling Data privacy Adaptation models Accuracy Generative adversarial networks (GANs) federated learning asynchronous molecular discovery

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Certificateless Edge-Assisted Encryption for IoT Devices: Enhancing Security and Performance

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第3期12卷 2930-2942页

作者： Cui, Xinhua Tian, Youliang Zhang, Xinyu Lin, Hongwei Li, Mengqian Guizhou Univ Coll Comp Sci & Technol State Key Lab Publ Big Data Guiyang 550025 Peoples R China Guizhou Normal Univ Sch Econ & Management Guiyang 550025 Peoples R China

In edge computing environments, the rapid growth of Internet of Things (IoT) devices presents significant challenges for data processing. These devices are often resource-constrained, leading to a tradeoff between achieving efficiency and ensuring security. On one hand, traditional certificateless encryption methods are computationally expensive;on the other hand, offloading the computational load to third-party entities can enhance efficiency but still introduces security risks. To address these issues, this article proposes a novel lightweight certificateless edge-assisted encryption scheme (CL-EAED). Ours scheme offloads computationally intensive tasks to edge servers, ensuring that edge-assisted processing does not expose sensitive information and only needs to be performed once. This approach effectively prevents data leakage and enhances both the efficiency and security of task offloading. Moreover, the CL-EAED scheme achieves IND-CCA security in standard model (SM) and has been validated using the ProVerif tool. Experimental evaluations demonstrate that CL-EAED eliminates the dependency on computationally intensive pairing operations, significantly reducing computational and communication costs. It outperforms existing solutions in terms of energy consumption, latency, and scalability, fully meeting the requirements of practical applications.

关键词： Encryption Internet of Things Data processing Performance evaluation Cryptography computational modeling Edge computing Servers Scalability Real-time systems Certificateless cryptography edge assisted IoT devices Internet of Things (IoT) lightweight resource constrained standard model (SM)

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：