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

Prediction of Myocardial Infarction Based on Non-ECG Sleep Data Combined With Domain Knowledge

引用

IEEE ACCESS 2025年 13卷 42262-42271页

作者： Li, Changyun Zhao, Yonghan Mo, Qihui Wang, Zhibing Xu, Xi Hunan Univ Technol Sch Comp Sci Zhuzhou 412007 Peoples R China Hunan Univ Technol Hunan Key Lab Intelligent Informat Percept & Proc Zhuzhou 412007 Peoples R China

Prediction of myocardial infarction (MI) is crucial for early intervention and treatment. Machine learning has increasingly been applied in the realm of disease prediction. This study explores the feasibility of utilizing easily obtainable heart rate (HR) and respiratory rate (RR) data collected during nocturnal sleep, in conjunction with clinical characteristics and medical domain knowledge, to predict MI. Data for this investigation were sourced from the Sleep Heart Health Study (SHHS) program in the United States, which was categorized into MI and non-MI groups based on the occurrence or absence of MI during follow-up, involving a total of 488 participants. Multiple features related to HR and RR were extracted and integrated with clinical features;four algorithms-MLP, SVM, XGBoost, and CNN-were employed for model construction. The findings indicated that the MLP model exhibited superior performance, achieving an accuracy rate 71.1%. Furthermore, three medical rules age, HR, and RR were incorporated into the MLP model to mitigate the limitations of small sample sizes. The experiments demonstrate that the model's accuracy reaches its optimal level by combining the age rule, improving to 73.1%. The findings indicate that leveraging non-cardiac electrophysiological data obtained during sleep alongside medical domain knowledge can significantly enhance the accuracy of early predictions regarding cardiac MI while offering novel insights for its prevention and diagnosis.

关键词： Myocardium Machine learning Biomedical monitoring Medical diagnostic imaging Cardiovascular diseases Predictive models Monitoring Accuracy Electrocardiography Heart rate variability Myocardial infarction machine learning sleep non-ECG domain knowledge guidance

来源：评论

学校读者我要写书评

暂无评论

Heuristic genetic algorithm parameter optimizer: Making lossless compression algorithms efficient and flexible

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 272卷

作者： Wang, Weijie Chen, Wenhui Yan, Li Yang, Yanqing Zhao, Huihuang Hengyang Normal Univ Coll Comp Sci & Technol Hengyang 421002 Peoples R China Hengyang Normal Univ Hunan Prov Key Lab Intelligent Informat Proc & App Hengyang 421002 Peoples R China Hunan Univ Natl Engn Lab Robot Visual Percept & Control Techn Hengyang Peoples R China

The processing of large volumes of time series data across various fields presents significant challenges, particularly when it comes to effectively managing floating-point numbers. Current dual precision floatingpoint lossless compression algorithms often struggle to deliver exceptional performance on diverse datasets, highlighting their inherent limitations. To address this issue, we propose a novel method called the Heuristic Genetic Algorithm Parameter Optimizer for Lossless Compression of Time Series Floating Point Data (HGAACTF). This method features a highly effective parameter optimizer designed specifically for compression algorithms that utilize leading zeros. The combination of our parameter optimizer and the HGA-ACTF algorithm strategy has been proven to outperform existing leading compression algorithms across multiple fields. This approach not only enhances the compression ratio but also significantly reduces both compression and decompression times. In our comparative study, we evaluated the HGA-ACTF algorithm against eleven well- performing algorithms and a variant of the algorithm, integrating our parameter optimizer and algorithmic strategy into other adaptable algorithms, and demonstrating notable improvements. Experimental results indicate that the HGA-ACTF algorithm achieves an average compression ratio improvement of 38.87%, with some datasets showing improvements of up to 54.36%. Our approach effectively addresses the transmission and storage of time series data, significantly reducing the overhead associated with data processing. The code can be found at https://***/wwj10/HGA-ACTF.

关键词： Time series floating point data Lossless compression Internet of things Compression algorithm Heuristic genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Elastic Supernet with Dynamic Training for JPEG steganalysis

引用

SIGNAL procESSING 2025年 236卷

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

JPEG is the predominant image format across social networks, serving as a prime cover medium for image steganography. However, previous deep learning models for JPEG steganalysis heavily rely on domain expertise and tedious trial-and-error methods. In this paper, we propose a two-stage neural architecture search scheme for JPEG steganalysis, based on Elastic Supernet with Dynamic Training (ESDT). The method involves constructing a weight-nesting supernet, with the largest subnetwork pretrained on ImageNet (a large-scale visual database widely used for pretraining deep learning models) and finetuning for JPEG steganalysis. Based on this pretrained network, we aim to enhance the model's performance in downstream tasks while reducing reliance on domain knowledge. A progressive shrinking strategy is introduced during supernet training to accommodate the need of elastic kernel sizes, depths, and widths. In the final stage, we utilize a performance predictor to identify the optimal subnetwork within the refined supernet. Extensive experiments showcase the method's superiority over state-of-the-art methods in JPEG steganalysis, achieving lower computational costs and superior generalization performance.

关键词： Steganalysis Steganography Neural architecture search Automated machine learning

来源：评论

学校读者我要写书评

暂无评论

Flower image classification based on an improved lightweight neural network with multi-scale feature fusion and attention mechanism

引用

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2023年第8期20卷 13900-13920页

作者： Zeng, Zhigao Huang, Cheng Zhu, Wenqiu Wen, Zhiqiang Yuan, Xinpan Hunan Univ Technol Sch Comp Sci Zhuzhou 412007 Hunan Peoples R China Hunan Key Lab Intelligent Informat Percept & Proc Zhuzhou 412007 Hunan Peoples R China

In order to solve the problem that deep learning-based flower image classification methods lose more feature information in the early feature extraction process, and the model takes up more storage space, a new lightweight neural network model based on multi-scale feature fusion and attention mechanism is proposed in this paper. First, the AlexNet model is chosen as the basic framework. Second, a multi-scale feature fusion module (MFFM) is used to replace the shallow single-scale convolution. MFFM, which contains three depthwise separable convolution branches with different sizes, can fuse features with different scales and reduce the feature loss caused by singlescale convolution. Third, two layers of improved Inception module are first added to enhance the extraction of deep features, and a layer of hybrid attention module is added to strengthen the focus of the model on key information at a later stage. Finally, the flower image classification is completed using a combination of global average pooling and fully connected layers. The experimental results demonstrate that our lightweight model has fewer parameters, takes up less storage space and has higher classification accuracy than the baseline model, which helps to achieve more accurate flower image recognition on mobile devices.

关键词： flower image classification multi-scale feature fusion depthwise separable convolution attention mechanism

来源：评论

学校读者我要写书评

暂无评论

MDFusion: Multi-Dimension Semantic-Spatial Feature Fusion for LiDAR-Camera 3D Object Detection

引用

REMOTE SENSING 2025年第7期17卷 1240-1240页

作者： Qiao, Renzhong Yuan, Hao Guan, Zhenbo Zhang, Wenbo Xidian Univ Sch Elect Engn Xian 710071 Peoples R China CETC 54th Res Inst Shijiazhuang 050081 Peoples R China Hebei Key Lab Intelligent Informat Percept & Proc Shijiazhuang 050081 Peoples R China

Accurate 3D object detection is becoming increasingly vital for the development of robust perception systems, particularly in applications such as autonomous driving vehicles and robotic systems. Many existing approaches rely on bird's eye view (BEV) feature maps to facilitate multi-modal interaction, as BEV representations enable efficient operations. However, the inherent sparsity of LiDAR BEV features often leads to misalignment with the dense semantic information in camera images, resulting in suboptimal fusion quality and degraded detection performance, especially in complex and dynamic environments. To mitigate these issues, this paper proposes a novel multi-dimension semantic-spatial feature fusion (MDFusion) method that combines LiDAR and image features in 2D and 3D spaces. Specifically, image semantic features are extracted using the DeeplabV3 segmentation network, which captures rich contextual information and is aligned with LiDAR point cloud voxel features through a summation operation to achieve precise semantic fusion. Additionally, LiDAR BEV features are fused with downsampled image features in 2D space via concatenation and spatially adaptive dilated convolution. The mechanism dynamically adjusts to the spatial characteristics of the data, ensuring robust feature integration. Extensive experiments on the KITTI and ONCE datasets demonstrate that our method achieves competitive performance in complex scenes, significantly improving the multi-modal fusion quality and detection accuracy while maintaining computational efficiency.

关键词： 3D object detection multi-dimension feature fusion multi-modal

来源：评论

学校读者我要写书评

暂无评论

Audio Multi-View Spoofing Detection Framework Based on Audio-Text-Emotion Correlations

引用

IEEE TRANSACTIONS ON informatION FORENSICS AND SECURITY 2024年 19卷 7133-7146页

作者： Wu, Junyan Yin, Qilin Sheng, Ziqi Lu, Wei Huang, Jiwu Li, Bin Sun Yat sen Univ Sch Comp Sci & Engn Guangdong Prov Key Lab Informat Secur Technol Minist EducKey Lab Informat Technol Guangzhou 510006 Peoples R China Shenzhen MSU BIT Univ Fac Engn Guangdong Lab Machine Percept & Intelligent Comp Shenzhen 518116 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Shenzhen Key Lab Media Secur Shenzhen 518060 Peoples R China

In recent years, audio spoofing detection has received widespread attention for protecting personal privacy and social security. Despite the significant progress achieved in audio single-view spoofing detection, challenges remain with regard to addressing unknown spoofing attacks in realistic scenarios. To solve these challenging problems, in this paper, we introduce a novel audio multi-view spoofing detection framework (AMSDF), whose goal is to capture both intra-view and inter-view cues by measuring correlations within audio multi-view features (i.e., audio-emotion-text) for audio spoofing detection. In general, different view features are inherently interconnected in the real patterns, while they may present unnatural correlations in the spoofing patterns. Therefore, more discriminative cues can be mined by utilizing their complex interactions, which is beneficial to the audio spoofing detection task. To this end, an intra-view graph attention mechanism (IGAM) is first utilized to aggregate each intra-view node within the same view. Subsequently, a heterogeneous graph fusion module (HGFM) is applied to measure correlations within inter-view nodes, which are enhanced with a master node for comprehensive analysis purposes. Finally, a group-based readout scheme (GRS) is designed to capture and preserve the most distinctive cues by leveraging the strengths of different feature sets, thereby effectively distinguishing subtle differences between real and spoofing audio. The experimental results show that our proposed framework can achieve better performance than that of the state-of-the-art methods, especially in realistic scenarios. The code and pre-trained models are available at https://***/ItzJuny/AMSDF.

关键词： Multimedia forensics audio spoofing detection multi-view learning graph attention mechanism Multimedia forensics audio spoofing detection multi-view learning graph attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Towards generalizable and robust image tampering localization with multi-task learning and contrastive learning

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 270卷

作者： Li, Haodong Zhuang, Peiyu Su, Yang Huang, Jiwu Shenzhen Univ Guangdong Prov Key Lab Intelligent Informat Proc Shenzhen Peoples R China Shenzhen Univ Shenzhen Key Lab Media Secur Shenzhen Peoples R China Shenzhen MSU BIT Univ Fac Engn Guangdong Lab Machine Percept & Intelligent Comp Shenzhen Peoples R China Shenzhen Univ SZU AFS Joint Innovat Ctr AI Technol Shenzhen Peoples R China

To prevent the misuse of tampered images, numerous tampering localization methods have been proposed in recent years. However, these methods often suffer from significant performance degradation when applied to testing images sourced from different datasets, subjected to post-processing (such as JPEG compression or resizing), or circulated through online social networks. The poor generalization and robustness of these techniques present a major obstacle to their practical application. This paper addresses these challenges by directly refining the feature representation and enhancing the diversity of training data. The proposed method utilizes a multi-task learning framework that focuses on tampering localization and image restoration. Both tasks share the same encoder, enabling the model to learn intrinsic, content-independent characteristics and capture more comprehensive features. Additionally, we integrate a contrastive learning module with a localization-aware sampling strategy. This module enhances feature representation, improving the model's ability to distinguish between tampered and authentic regions. Moreover, the localization branch is trained with two types of augmented images, one from the data augmentation module and the other from the restoration branch. Experiments evaluated on four public datasets show that the proposed method achieves superior generalization and robustness compared to existing approaches. The code is available at https: //***/media-sec-lab/MTCL.

关键词： Image forensics Tampering localization Multi-task learning Contrastive learning Robust against post-processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Dynamic Analysis for Malware Detection With Gradient Attack

引用

IEEE SIGNAL procESSING LETTERS 2024年 31卷 2825-2829页

作者： Yan, Pei Tan, Shunquan Wang, Miaohui Huang, Jiwu Shenzhen Key Lab Media Secur Shenzhen 518000 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen City Polytech Sch Informat & Commun Technol Shenzhen 518116 Peoples R China Shenzhen MSU BIT Univ Guangdong Lab Machine Percept & Intelligent Comp Fac Comp Shenzhen 518116 Peoples R China

Malware detection is an effective way to prevent the intrusion of malware into computer systems, and the API-based dynamic analysis method can effectively detect obfuscated and packaged malware. However, existing methods still suffer from limited detection accuracy and weak generalization. To address this issue, this paper presents a gradient attack-based malware dynamic analysis method. Through exerting adversarial noise into the embedding layer, the malware detection model can learn more robust representations of API sequences during training, achieving broader coverage of sample representations. The strategy of normalizing attack noise and recovering attacked representation is designed, which controls the strength of the gradient attack within a reasonable range and prevents a negative impact on the model's detection performance. The proposed method can be applied to existing API-based malware detection models to enhance their detection performance, indicating the strong generality of the proposed method. Experimental results on two benchmark datasets (i.e., Aliyun and Catak) demonstrate the effectiveness of the proposed gradient attack method, which further improves the detection performance of the mainstream API-based models, with an average accuracy increase of 2.80% and 3.66% on these two datasets, respectively.

关键词： Malware Training Noise Feature extraction Application programming interfaces Perturbation methods Backpropagation Vocabulary Vectors Accuracy Adversarial method dynamic analysis malware detection network security

来源：评论

学校读者我要写书评

暂无评论

Spontaneous Temporal Grouping Neural Network for Long-Term Memory Modeling

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2022年第2期14卷 472-484页

作者： Shan, Dongjing Zhang, Xiongwei Zhang, Chao Army Engn Univ Lab Intelligent Informat Proc Nanjing 210007 Peoples R China Peking Univ Key Lab Machine Percept MOE Beijing 100871 Peoples R China

The capacity of long-term memory is an important issue in sequence learning, but it remains challenging for the problems of vanishing gradients or out-of-order dependencies. Inspired by human memory, in which long-term memory is broken into fragments and then can be recalled at appropriate times, we propose a neural network via spontaneous temporal grouping in this article. In the architecture, the segmented layer is used for spontaneous sequence segmentation under guidance of the reset gates which are driven to be sparse in the training process;the cascading layer is used to collect information from the temporal groups, where a filtered long short-term memory with chrono-initialization is proposed to alleviate the gradient vanishing phenomenon, and random skip connections are adopted to capture complex dependencies among the groups. Furthermore, the advantage of our neural architecture in long-term memory is demonstrated via a new measurement method. In experiments, we compare the performance with multiple models on several algorithmic or classification tasks, and both of the sequences with fixed lengths like the MNISTs and with varying lengths like the speech utterances are adopted. The results in different criteria have demonstrated the superiority of our proposed neural network.

关键词： Computer architecture Logic gates Microprocessors Training Standards Data models Task analysis Long-term memory recurrent neural network temporal dependency temporal grouping vanishing gradient

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：