检索结果-内蒙古大学图书馆

TruVRF: Toward Triple-Granularity Verification on Machine Unlearning

IEEE Transactions on Information Forensics and Security 2025年 20卷 4844-4859页

作者： Zhou, Chunyi Gao, Yansong Fu, Anmin Chen, Kai Zhang, Zhi Xue, Minhui Dai, Zhiyang Ji, Shouling Zhang, Yuqing Zhejiang University College of Computer Science and Technology Hangzhou310027 China Nanjing University of Science and Technology College of Computer Science and Engineering Nanjing210094 China The University of Western Australia School of Computer Science and Software Engineering PerthWA6009 Australia Chinese Academy of Sciences Beijing100864 China Data61 CSIRO SydneyNSW2122 Australia Nanjing University of Science and Technology School of Cyber Science and Engineering Nanjing210094 China University of Chinese Academy of Sciences National Computer Network Intrusion Protection Center Beijing101408 China

The right to be forgotten has incentivized machine unlearning, but a key challenge persists: the lack of reliable methods to verify unlearning conducted by model providers. This gap facilitates dishonest model providers to deceive data contributors. Current approaches often rely on invasive methods like backdoor injection. However, it poses security concerns and is also inapplicable to legacy data—already released data. To tackle this challenge, this work initializes the first non-invasive unlearning verification framework which operates at triple-granularity (class-, volume-, sample-level) to assess the data facticity and volume integrity of machine unlearning. In this paper, we propose a framework, named TruVRF, encompasses three Unlearning-Metrics, each tailored to counter different types of dishonest model providers or servers (Neglecting Server, Lazy Server, Deceiving Server). TruVRF leverages non-invasive model sensitivity to enable multi-granularity verification of unlearning. Specifically, Unlearning-Metric-I checks if the removed class matches the data contributor’s unlearning request, Unlearning-Metric-II measures the amount of unlearned data, and Unlearning-Metric-III validates the correspondence of a specific unlearned sample with the requested deletion. We conducted extensive evaluations of TruVRF efficacy across three datasets, and notably, we also evaluated the effectiveness and computational overhead of TruVRF in real-world applications for the face recognition dataset. Our experimental results demonstrate that TruVRF achieves robust verification performance: Unlearning-Metric-I and -III achieve over 90% verification accuracy on average against dishonest servers, while Unlearning-Metric-II maintains an inference deviation within 4.8% to 8.2%. Additionally, TruVRF demonstrates generalizability across diverse conditions, including varying numbers of unlearned classes and sample volumes. Significantly, TruVRF is applied to two state-of-the-art unlearnin

关键词： Data models Servers Sensitivity Solid modeling Data privacy Computational modeling Context modeling Adaptation models Analytical models Volume measurement

来源：评论

学校读者我要写书评

暂无评论

Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images

Prompting DirectSAM for Semantic Contour Extraction in Remot...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Miao, Shiyu Chen, Delong Liu, Fan Zhang, Chuanyi Gu, Yanhui Guo, Shengjie Zhou, Jun College of Computer Science and Software Engineering Hohai University Nanjing China Hong Kong University of Science and Technology Hong Kong School of Computer and Electronic Information Nanjing Normal University Nanjing China School of Information and Communication Technology Griffith University QLD Australia

ISBN: (纸本)9798350368741

The Direct Segment Anything Model (DirectSAM) excels in class-agnostic contour extraction. In this paper, we explore its use by applying it to optical remote sensing imagery, where semantic contour extraction-such as identifying buildings, road networks, and coastlines-holds significant practical value. Those applications are currently handled via training specialized small models separately on small datasets in each domain. We introduce a foundation model derived from DirectSAM, termed DirectSAM-RS, which not only inherits the strong segmentation capability acquired from natural images, but also benefits from a large-scale dataset we created for remote sensing semantic contour extraction. This dataset comprises over 34k image-text-contour triplets, making it at least 30 times larger than individual dataset. DirectSAM-RS integrates a prompter module: a text encoder and cross-attention layers attached to the DirectSAM architecture, which allows flexible conditioning on target class labels or referring expressions. We evaluate the DirectSAM-RS in both zero-shot and fine-tuning setting, and demonstrate that it achieves state-of-the-art performance across several downstream benchmarks. © 2025 IEEE.

关键词： Remote sensing Semantic contour extraction Vision-language learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Using Machine Learning for Accurate Detection of DDoS Attack in software Defined Network 2nd

A Novel Approach Using Machine Learning for Accurate Detecti...

引用

2nd International Conference on Cyber Intelligence and Information Retrieval, CIIR 2023

作者： Sharma, Hitesh Kumar Choudhury, Tanupriya Kotecha, Ketan Mahdi, Hussain Falih Dutta, Soumi Bhattacharya, Abhishek Sar, Ayan Energy Acres Bidholi Uttarakhand Bidholi India School of Computer Science University of Petroleum and Energy Studies Uttarakhand Dehradun India Pune India Pune India Department of Computer and Software Engineering University of Diyala Baquba Iraq Sister Nivedita University Chakpachuria India

ISBN: (纸本)9789819776023

A denial Of Service (DoS) attack is termed an attack when the request-receiving server or network shuts down or becomes inaccessible for service. This kind of attack is caused by flooding the target server or network with huge traffic or sending information which can trigger a vulnerability to the server and lead to server crash. Different kinds of DoS attacks can occur on a network including a classic DoS attack which is carried out by a single client machine sending tons of requests and data to a server by itself to increase its processing to the extent that no new genuine requests are answered by the server and network is ultimately unreachable. Another kind of DoS attack is termed a DDoS (Distributed Denial Of Service) attack which includes a master host machine that leverages the network of machines around it to send multiple requests to the server from different machines which act as zombie machines for the attack as the machine won’t even have an idea itself that they are being used for an attack on the server. As multiple requests and data hits the server from different locations, the server becomes unavailable for processing and leads to network failure. These zombie machines are termed botnets which are connected online and are used to overwhelm a target website with fake traffic. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Phoneme Classification in Imagined Speech Using Explainable Machine Learning 13

Phoneme Classification in Imagined Speech Using Explainable ...

引用

13th International Winter Conference on Brain-computer Interface, BCI 2025

作者： Kim, Sejin Kang, Hyunwook Jeong, Ji-Hoon Lee, Minji Dept. Artificial Intelligence The Catholic University of Korea Bucheon Korea Republic of Dept. Electrical and Computer Engineering Inha University Incheon Korea Republic of Dept. Computer Science Chungbuk National University Cheongju Korea Republic of Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon Korea Republic of

ISBN: (纸本)9798331521929

Imagined speech is gaining attention as a next-generation paradigm for brain-computer interfaces in terms of its intuitiveness in communication. Many studies have focused on classifying imagined words as the basis of communication, but some studies on phoneme classification based on imagined speech have begun to be conducted in terms of the fact that combinations of phonemes can further expand sound images. In addition, explainability is a major issue in classification results in machine learning, but there have been few studies that analyzed the explainability of imagined speech classification. In this study, we examined explainability using SHAP for phoneme classification based on imagined speech. FEIS dataset was used, and 16 phonemes were classified using the XGBoost classifier. In 21 subjects, the average accuracy was 40.36%, the average precision was 41.7%, the average recall was 40.34%, and the average F1-score was 40.7%. In addition, when looking at Sub 04, which had the highest performance, the SHAP values were high in AF3 and F7 channels, which correspond to Wernicke’s area related to speech. In this regard, we could observe the feature importance of this area. These results prove that Wernicke’s area actually plays an important role in classifying phoneme units in imagined speech, and can provide important insights to improve the performance of imagined speech for intuitive communication based on brain-computer interface in the future. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Trustworthy Analysis Approach for Chatbots on Health Data: ChatGPT-4 Example

A Trustworthy Analysis Approach for Chatbots on Health Data:...

引用

International Scientific-Professional Conference on Information Technology (IT)

作者： Kübra Arslanoğlu Mehmet Karaköse The Department of Software Engineering The Faculty of Engineering The University of Firat Elazig The Department of Computer Engineering The Faculty of Engineering The University of Firat Elazig

ISBN: (数字)9798331517649

ISBN: (纸本)9798331517656

Considering the increasing and widespread use of chatbots, it is of great importance to provide methods and tools to address ethical concerns and to make users aware of various aspects of a chatbot, including non-functional features. The Generative Pre-Trained Transformer (GPT) is a state-of-the-art Natural Language Generation (NLG) model, enhanced by the latest version of GPT-4. This study evaluates the trustworthiness of the responses of three different chatbot models, BlenderBot with Hugging Face, ChatGPT-3.5 and ChatGPT-4, to 100 randomly selected medical questions. The accuracy and semantic similarity of the answers were measured by BLEU, ROUGE-1 and Cosine Similarity metrics, and response times were also recorded as an important performance factor. The results showed that GPT-4 exhibited superior performance, thus being able to produce more accurate and contextually reliable responses. However, the significantly longer response time of GPT-4 emerged as a disadvantage that may affect real-time utilisation. These findings provide an important reference for the effective use of GPT-4 in the context of health chatbots. The study contributes to the literature on improving the effectiveness of chatbots in healthcare by drawing attention to the importance of balancing speed, accuracy and trustworthiness, as well as the fact that the answers obtained are drawn with Application Programming Interface (API).

关键词： Accuracy Natural language generation Semantics Medical services Chatbots Transformers Real-time systems Time factors Reliability Application programming interfaces

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Potential of Self-Supervised Monocular Depth Estimation via Patch-Based Self-Distillation

引用

IEEE Internet of Things Journal 2025年第11期12卷 18042-18055页

作者： Yu, Ting Pan, Shan Chen, Wei Tian, Zijian Wang, Zehua Yu, F. Richard Leung, Victor C. M. Postdoctoral Research Station China RongTong Academy of Sciences Group Corporation Limited Beijing100022 China China RongTong Artificial Intelligence Research Center Beijing100022 China China University of Mining and Technology School of Artificial Intelligence Beijing100083 China China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China School of Artificial Intelligence Beijing100083 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

Perceiving scene depth and 3D structure is one of the key tasks for Internet of Video Things (IoVT) devices to understand and interact with the environment. Self-supervised monocular depth estimation has demonstrated significant potential in leveraging large-scale unlabeled datasets to achieve competitive performance, thereby playing an increasingly important role in depth estimation. Despite recent methods providing additional supervisory signals through self-distillation strategies to improve depth estimation, an effective method for generating pseudo-depth labels suitable for addressing occlusion issues among elements far from the camera remains unexplored. To address this limitation, we propose a Patch-based Self-Distillation Learning Framework to exploit the potential of self-supervised monocular depth estimation in recovering fine-grained scene depth. In the proposed framework, elements far from the camera within the input image are enlarged by enlarging and cropping operations in the patch-based self-distillation branch. Guided by photometric consistency, the model learns the detailed occlusion relationships among elements from the enlarged patches, producing patch depth maps with fine structures. In the main branch, which takes full-scale images as input, patch depth maps serve as pseudo-depth labels through self-distillation loss to provide additional supervisory signals for regions where photometric consistency fails to offer effective supervision. This forces the depth estimation network to recover fine structures of elements far from the camera in full-scale input images. Regarding the architecture of the depth estimation network, we introduce a bin-center prediction. In this prediction, a global aggregator based on self-attention provides additional scene structure queries for adaptive scene depth discretization. Finally, to encourage the model to explore more general cues for depth inference beyond road plane cues, we propose a PatchMix data augmentati

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

PathNetDRP: a novel biomarker discovery framework using pathway and protein–protein interaction networks for immune checkpoint inhibitor response prediction

引用

BMC Bioinformatics 2025年第1期26卷 1-24页

作者： Lee, Dohee Ahn, Jaegyoon Choi, Jonghwan Department of Computer Science and Engineering Incheon National University 119 Academy-ro Yeonsu-gu Incheon22012 Korea Republic of Division of Software Hallym University 1 Hallymdaehak-gil Gangwon-do Chuncheon24252 Korea Republic of

Background: Predicting immune checkpoint inhibitor (ICI) response remains a significant challenge in cancer immunotherapy. Many existing approaches rely on differential gene expression analysis or predefined immune signatures, which may fail to capture the complex regulatory mechanisms underlying immune response. Network-based models attempt to integrate biological interactions, but they often lack a quantitative framework to assess how individual genes contribute within pathways, limiting the specificity and interpretability of biomarkers. Given these limitations, we developed PathNetDRP, a framework that integrates biological pathways, protein-protein interaction networks, and machine learning to identify functionally relevant biomarkers for ICI response prediction. Results: We introduce PathNetDRP, a novel biomarker discovery approach that applies the PageRank algorithm to prioritize ICI-associated genes, maps them to relevant biological pathways, and calculates PathNetGene scores to quantify their contribution to immune response. Unlike conventional methods that focus solely on gene expression differences, PathNetDRP systematically incorporates biological context to improve biomarker selection. Validation across multiple independent cancer cohorts showed that PathNetDRP achieved strong predictive performance, with cross-validation the area under the receiver operating characteristic curves increasing from 0.780 to 0.940. Interestingly, PathNetDRP did not merely improve predictive accuracy;it also provided insights into key immune-related pathways, reinforcing its potential for identifying clinically relevant biomarkers. Conclusion: The biomarkers identified by PathNetDRP demonstrated robust predictive performance across cross-validation and independent validation datasets, suggesting their potential utility in clinical applications. Furthermore, enrichment analysis highlighted key immune-related pathways, providing a deeper understanding of their role in ICI res

关键词： Immune system

来源：评论

学校读者我要写书评

暂无评论

Emerging Approaches to Sugarcane Leaf Disease Classification: A Systematic Review

Emerging Approaches to Sugarcane Leaf Disease Classification...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： Zeel R Khambholja Premal Patel Computer Engineering (Software Engineering) Ipcowala Institute of Engineering & Technology Dharmaj Gujarat India DEPSTAR Charusat Gujarat India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Diseases that affect leaves are very common and their effect on the yields of crops mean that early diagnosis is important in reducing yield loss. It is reacting that in traditional approach to diagnosing of the broad dome plant diseases, people rely on observation and often it is highly time consuming, prone to errors, requires high level of expertise. Some approaches focused on using a computer vision system for classifying the diseases in the recent past where the present machine learning models provide a definite solution. However, these approaches come with some of the following challenges including, requirement of large data sets that are well labeled, dealing with variations in illumination conditions or environmental light settings and the applicability of the developed models for a wide range of plant species. The paper presents an analysis of the current trends of approaches used in classification of Sugarcane Leaf diseases and evaluates the merits and demerits of each of the approaches. The goal is to provide a survey of the development in this area and give direction for future study to deal with issues like the stability of models and their practical applicability.

关键词： Surveys Plant diseases Lighting Crops Machine learning Market research Stability analysis Data models Diseases Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Forecasting land use changes in crop classification and drought using remote sensing

引用

Journal of Arid Land 2025年第5期17卷 575-589页

作者： Mashael MAASHI Nada ALZABEN Noha NEGM Venkatesan VEERAMANI Sabarunisha Sheik BEGUM Geetha PALANIAPPAN Department of Software Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh 11451Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh 11671Saudi Arabia Department of Computer Science Applied College at MahayilKing Khalid UniversityAbha 61421Saudi Arabia Department of Civil Engineering University College of EngineeringAnna UniversityAriyalur 621731India Department of Biotechnology P.S.R.Engineering CollegeSivakasi 626140India Department of Electronics and Communication Engineering School of Engineering and TechnologyDhanalakshmi Srinivasan UniversitySamayapuram 621112India

Challenges in land use and land cover(LULC)include rapid urbanization encroaching on agricultural land,leading to fragmentation and loss of natural ***,the effects of urbanization on LULC of different crop types are less *** study assessed the impacts of LULC changes on agriculture and drought vulnerability in the Aguascalientes region,Mexico,from 1994 to 2024,and predicted the LULC in 2034 using remote sensing data,with the goals of sustainable land management and climate resilience *** increasing urbanization and drought,the integration of satellite imagery and machine learning models in LULC analysis has been underutilized in this *** Landsat imagery,we assessed crop attributes through indices such as normalized difference vegetation index(NDVI),normalized difference water index(NDWI),normalized difference moisture index(NDMI),and vegetation condition index(VCI),alongside watershed delineation and spectral *** random forest model was applied to classify LULC,providing insights into both historical and future *** indicated a significant decline in vegetation cover(109.13 km^(2))from 1994 to 2024,accompanied by an increase in built-up land(75.11 km^(2))and bare land(67.13 km^(2)).Projections suggested a further decline in vegetation cover(41.51 km^(2))and continued urban land expansion by *** study found that paddy crops exhibited the highest values,while common bean and maize performed *** analysis revealed that mildly dry areas in 2004 became severely dry in 2024,highlighting the increasing vulnerability of agriculture to climate *** study concludes that sustainable land management,improved water resource practices,and advanced monitoring techniques are essential to mitigate the adverse effects of LULC changes on agricultural productivity and drought resilience in the *** findings contribute to the understanding of how remote sensing can be effectively used for long-t

关键词： land use and land cover(LULC) crop attributes drought vulnerability machine learning models remote sensing

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：