检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Masrani, Teale W. He, Helen Ai Messier, Geoffrey Department of Computer Science University of Calgary Calgary Canada Electrical and Software Engineering University of Calgary Calgary Canada

On any night in Canada, at least 35,000 individuals experience homelessness. These individuals use emergency shelters to transition out of homelessness and into permanent housing. We designed and deployed a technology to support front-line staff at the largest emergency housing shelter in Calgary, Canada. Over a period of five months in 2022, we worked closely with front-line staff to co-design an interface for supporting a holistic understanding of client context and facilitating decision-making. The tool is currently in-use and our collaboration is ongoing. In this paper, we reflect on preliminary findings regarding the second iteration of the tool. We find that supporting shelter staff in understanding the human behind the data was a critical component of design. This work contributes to literature on how data tools may be integrated into homeless shelters in a way that aligns with shelters' values. Copyright © 2023, The Authors. All rights reserved.

关键词： Housing

Voice Presentation Attacks Detection using Acoustic MLTP Features and BiLSTM

学校读者我要写书评

暂无评论

Voice Presentation Attacks Detection using Acoustic MLTP Fea...

International Conference on Communication, Computing and Digital Systems (C-CODE)

作者： Sundas Ibrar Ali Javed Hafsa Ilyas Department of Computer Science UET Taxila Punjab Pakistan Department of Software Engineering UET Taxila Punjab Pakistan

Automatic speaker verification (ASV) systems have been used in numerous voice-controlled technologies including voice banking, automobiles, smartphones, smart homes, etc. The growth of voice-operated devices is increasing exponentially, and it is mandatory to secure the ASV systems against voice spoofing attacks such as cloned and synthetic voices. The research community has worked to develop spoofing countermeasures to improve the security of ASV systems. However, existing spoofing countermeasures have limitations to detect voice conversion, synthetic speech, and voice replay attacks. There still exists a need for the development of voice spoofing detectors to further strengthen the security of voice-controlled systems. Therefore, in this study, we designed a novel spoofing countermeasure for identifying physical access (PA) and logical access (LA) attacks. More precisely, we proposed a novel acoustic feature descriptor, namely, modified local ternary patterns (MLTP), and used them to train a BiLSTM classifier for voice spoofing detection. We assessed the performance of our approach using the standard ASVspoof-2019 dataset and attained an equal error rate (EER) of 1.87% and 2.66% for the PA and LA attacks, respectively. Experimental results obtained from a detailed assessment signify that our approach has the capability to accurately classify the bonafide and spoofed audio samples over contemporary methods.

关键词：

Multimodal Attention-Enhanced Feature Fusion-based Weekly Supervised Anomaly Violence Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kaneko, Yuta Musa Miah, Abu Saleh Hassan, Najmul Lee, Hyoun-Sup Jang, Si-Woong Shin, Jungpil School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Japan Department of Applied Software Engineering Dongeui University Busanjin-Gu Busan47340 Korea Republic of Department of Computer Engineering Dongeui University Busan47340 Korea Republic of

Weakly supervised video anomaly detection (WS-VAD) is a crucial area in computer vision for developing intelligent surveillance systems. Researchers are actively working on WS-VAD systems by assessing anomaly scores, but challenges persist due to ineffective feature extraction from unimodal approaches. Additionally, limited research on multimodal datasets has led to unsatisfactory performance accuracy. To address the challenges, We propose a multimodal attention-enhanced feature fusion-based system for weakly supervised anomaly detection. This system uses three feature streams: RGB video, optical flow, and audio signals, where each stream extracts complementary spatial and temporal features using an enhanced attention module to improve detection accuracy and robustness. In the first stream, we employed an attention-based, multi-stage feature enhancement approach to improve spatial and temporal features from the RGB video where the first stage consists of a ViT-based CLIP module, with top-k features concatenated in parallel with I3D and Temporal Contextual Aggregation (TCA) based rich spatiotemporal features. The second stage effectively captures temporal dependencies using the Uncertainty-Regulated Dual Memory Units (UR-DMU) model, which learns representations of normal and abnormal data simultaneously, and the third stage is employed to select the most relevant spatiotemporal features. The second stream extracted enhanced attention-based spatiotemporal features from the flow data modality-based feature by taking advantage of the integration of the deep learning and attention module. The audio stream captures auditory cues using an attention module integrated with the VGGish model, aiming to detect anomalies based on sound patterns. These streams enrich the model by incorporating motion and audio signals often indicative of abnormal events undetectable through visual analysis alone. The concatenation of the multimodal fusion leverages the strengths of each modality,

关键词： Audio streaming

Interaction Petri Nets for Modeling Multiagent Interactions

学校读者我要写书评

暂无评论

Interaction Petri Nets for Modeling Multiagent Interactions

computer science, computer engineering, & Applied Computing (CSCE), Congress in

作者： Norah Aldahash Steve King Abir Benabid Computer Science University of York York UK Software Engineering King Saud University Riyadh Saudi Arabia

Petri nets have been closely related to multiagent systems (MAS) and used as a tool for modeling agents and their behavior for specification, verification, and validation purposes. Various models of agent activities, plans, and interactions show the ability of Petri nets to represent dynamic and concurrent MAS. Insight from previous Petri net models of agent interaction led to the proposal of a Colored Petri net model for monitoring the state of communication. This paper presents an interaction Colored Petri net for modeling message-based communication ruled by Interaction Protocols (IP). While previous works focused on modeling a single protocol, the proposed Interaction Petri Net (IPN) allows specifying multiple protocols within one model. Moreover, IPN allows the detection of common communication errors such as: lost messages, delay, busy-wait and agent termination. In IPN, an interaction protocol is specified as a Petri net marking where tokens are message instances. This approach enables the capture of the status of each IP in real-time for error detection where two possible approaches have been examined. The proposed model has been validated through a comparison analysis with a previous Petri net model of interaction.

关键词：

A2RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jiawei Yu, Hongwei Chen, Jiansheng Ding, Xinlong Wang, Jinlong Liu, Jinyuan Zou, Bochao Ma, Huimin School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Software Technology Dalian University of Technology Dalian China

Infrared and visible image fusion (IVIF) is a crucial technique for enhancing visual performance by integrating unique information from different modalities into one fused image. Exiting methods pay more attention to conducting fusion with undisturbed data, while overlooking the impact of deliberate interference on the effectiveness of fusion results. To investigate the robustness of fusion models, in this paper, we propose a novel adversarial attack resilient network, called A2RNet. Specifically, we develop an adversarial paradigm with an anti-attack loss function to implement adversarial attacks and training. It is constructed based on the intrinsic nature of IVIF and provide a robust foundation for future research advancements. We adopt a Unet as the pipeline with a transformer-based defensive refinement module (DRM) under this paradigm, which guarantees fused image quality in a robust coarse-to-fine manner. Compared to previous works, our method mitigates the adverse effects of adversarial perturbations, consistently maintaining high-fidelity fusion results. Furthermore, the performance of downstream tasks can also be well maintained under adversarial attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Image fusion

Identity-preserving 3D Facial Completion under Skull Constraints

学校读者我要写书评

暂无评论

Identity-preserving 3D Facial Completion under Skull Constra...

IEEE International Joint Conference on Biometrics (IJCB)

作者： Longtao Yu Junli Zhao Fuqing Duan Chenlei Lv Dantong Li Zhenkuan Pan Mingquan Zhou College of Computer Science and Technology Qingdao University School of Artificial Intelligence Beijing Normal University College of Computer Science and Software Engineering Shenzhen University School of Computer Science and Informations Cardiff University School of Information Science and Technology Northwest University National and Local Joint Engineering Research Center for Cultural Heritage Digitization Northwest University

ISBN: (数字)9798350364132

ISBN: (纸本)9798350364149

3D face shape completion is a necessary pre-process for various facial applications as they are often mutilated due to the acquiring environment or occlusion. However, it is challenging to ensure identity consistency when completing faces with large missing regions. Therefore, we introduce craniofacial information to supervise the completion of face shapes. Firstly, a novel dual encoder-decoder structure for face depth image inpainting is constructed by combining dilated convolution and the coherent semantic attention mechanism, guaranteed to generate smooth results with complete semantic information even in the presence of large missing regions in the face model. Then, we innovatively design a craniofacial superimposition module to determine the probability that the inpainted face and corresponding skull come from the same person, constraining the inpainting network to learn identity consistency information. Finally, extensive experimental results show that our method can effectively complete 3D face shapes containing large arbitrary missing regions while guaranteeing identity consistency.

关键词： Biometrics Three-dimensional displays Attention mechanisms Shape Convolution Semantics Faces

A Distributed Privacy-Preserving Framework for Deep Learning with Edge-Cloud Computing 15

学校读者我要写书评

暂无评论

A Distributed Privacy-Preserving Framework for Deep Learning...

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart Data, SmartData 2022

作者： Dai, Fei Liu, Guozhi Huang, Bi Xu, Xiaolong Chen, Chaochao Zhou, Zhangbing Zhou, Xiaokang Southwest Forestry University School of Big Data and Intelligent Engineering Kunming China Nanjing University of Information Science and Technology School of Computer and Software Nanjing China Zhejiang University College of Computer Science and Technology Zhejiang China China University of Geosciences School of Information Engineering Beijing China Shiga University Faculty of Data Science Shiga Japan

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

Industrial Internet of Things (IIoT) systems can leverage deep learning (DL) models to provide intelligent applications. However, the training process of such DL models tends to leak privacy when the training data contain sensitive operational and management information. Most studies about privacy-preserving DL require a trusted data collector and thus are not suitable in an untrusted environment. In this paper, we propose a distributed privacy-preserving framework for DL with edge-cloud computing, where direct privacy leakage and indirect privacy leakage of training data are both considered. First, a pre-trained convolutional neural network (CNN) is partitioned into two parts for limiting direct privacy leakage of raw data, namely the feature module and the classification module. The feature module consisting of the lower layers of the CNN is deployed on an edge server, which is used to attract the feature of raw data. The feature data is fed to the classification module consisting of the higher layers of the CNN, which is deployed on the cloud server to compute image classification tasks. Second, a perturbation module between the feature module and the classification module is designed for limiting indirect privacy leakage during feature data transmission. The perturbation module uses local differential privacy (LDP) to produce noise in the feature data. Third, to further improve the accuracy, we retrain the classification module with the randomized feature data from edge servers. Experimental results show that the proposed framework achieves high accuracy under low privacy budgets. © 2022 IEEE.

关键词： Classification (of information)

Privacy-preserving polyp segmentation using federated learning with differential privacy

学校读者我要写书评

暂无评论

Smart Health 2025年 36卷

作者： Hasan, Md. Mahmodul Rahman, Mohammad Motiur Department of Software Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Bangladesh Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University Tangail 1902 Bangladesh

Background and Objective: Patient privacy is of paramount importance in the medical field, especially as data-driven medical applications gain popularity. The privacy of medical records is increasingly crucial. In this context, data-oriented polyp (a precancerous stage of colon cancer) segmentation is a critical area of ongoing research, aiming to improve automated segmentation. Accurate segmentation is essential for the complete removal of these overgrown cells from the gastrointestinal system. Although large data sets using data-driven algorithms have shown excellent performance in image segmentation, privacy concerns have limited the availability of such datasets for medical image segmentation tasks, including polyp segmentation. This research aims to develop an approach for polyp segmentation that combines data from multiple sources without compromising patient privacy. Methods: We design a differentially private federated learning system to segment polyps without compromising privacy. Our approach employs the encoder–decoder architecture UNet 3+ with a deep supervision technique to achieve effective segmentation of polyps in a federated setup. The federated training process aims to find generalized global models for the entities participating in the federation. The study uses four public databases to train and evaluate the proposed method. Results: The proposed privacy-protected technique demonstrates promising outcomes in polyp segmentation, achieving an average Intersection over Union (IoU) score of 0.90881 ± 0.00355 over four publicly available datasets. Evaluation metrics include precision, sensitivity, and specificity values, indicating the effectiveness of our approach in accurately segmenting polyps. Conclusions: Our differentially private federated learning system successfully segments polyps without compromising patient privacy. The promising results suggest that this approach can significantly contribute to the field of polyp segmentation, facilitatin

关键词： Federated learning Image segmentation Polyp segmentation Secured medical image classification

Cultivating software Quality Improvement in the Classroom: An Experience with ChatGPT

学校读者我要写书评

暂无评论

Cultivating Software Quality Improvement in the Classroom: A...

Conference on software engineering Education & Training (CSEE&T)

作者： Eman Abdullah AlOmar Mohamed Wiem Mkaouer Software Engineering Department Stevens Institute of Technology Hoboken NJ USA Computer Science Department University of Michigan-Flint Flint MI USA

ISBN: (数字)9798350378979

ISBN: (纸本)9798350378986

Large Language Models (LLMs), like ChatGPT, have gained widespread popularity and usage in various software engineering tasks, including programming, testing, code review, and program comprehension. However, their effectiveness in improving software quality in the classroom remains uncertain. In this paper, our aim is to shed light on our experience in teaching the use of Programming Mistake Detector (PMD) to cultivate a bugfix culture and leverage LLMs to improve software quality in educational settings. This paper discusses the results of an experiment involving 102 submissions that carried out a code review activity of 1,230 rules. Our quantitative and qualitative analysis reveals that a set of PMD quality issues influences the acceptance or rejection of the issues, and design-related categories that take longer to resolve. Although students acknowledge the potential of using ChatGPT during code review, some skepticism persists. We envision our findings to enable educators to support students with code review strategies to raise students' awareness about LLMs and promote software quality in education.

关键词： Codes Reviews Large language models Education software quality Detectors Chatbots

Provably Secure Non-interactive Key Exchange Protocol for Group-Oriented Applications in Scenarios with Low-Quality Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Rui Zhang, Lei Computer Science and Artificial Intelligence Institute Southwestern University of Finance and Economics China Software Engineering Institute East China Normal University China

Non-interactive key exchange (NIKE) enables two or multiple parties (just knowing the public system parameters and each other’s public key) to derive a (group) session key without the need for interaction. Recently, NIKE in multi-party settings has been attached importance. However, we note that most existing multi-party NIKE protocols, underlying costly cryptographic techniques (i.e., multilinear maps and indistinguishability obfuscation), lead to high computational costs once employed in practice. Therefore, it is a challenging task to achieve multiparty NIKE protocols by using more practical cryptographic primitives. In this paper, we propose a secure and efficient NIKE protocol for secure communications in dynamic groups, whose construction only bases on bilinear maps. This protocol allows multiple parties to negotiate asymmetric group keys (a public group encryption key and each party’s decryption key) without any interaction among one another. Additionally, the protocol supports updating of group keys in an efficient and non-interactive way once any party outside a group or any group member joins or leaves the group. Further, any party called a sender (even outside a group) intending to connect with some or all of group members called receivers in a group, just needs to generate a ciphertext with constant size under the public group encryption key, and only the group member who is the real receiver can decrypt the ciphertext to obtain the session key. We prove our protocol captures the correctness and indistinguishability of session key under k-Bilinear Diffie-Hellman exponent (k-BDHE) assumption. Efficiency evaluation shows the efficiency of our protocol. Copyright © 2024, The Authors. All rights reserved.

关键词： Efficiency