A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
Secure Object Detection Based on Deep Learning
2021
Journal of Information Processing Systems
Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. ...
Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. ...
[37] introduced differential privacy (DP) to preserve privacy in deep learning models. ...
doi:10.3745/jips.03.0161
dblp:journals/jips/KimJ21
fatcat:hgrxur6kfbbirjo7b5dpgs4oim
Special issue on new advanced techniques in security of artificial intelligence
2022
Journal of Ambient Intelligence and Humanized Computing
Efficient Privacy-Preserving Data Aggregation Algorithm". ...
Privacy-preserving of AI data is an important research point. ...
doi:10.1007/s12652-021-03645-4
fatcat:mte2dyq22zfjpext5zhnoqbqka
Vision Through the Veil: Differential Privacy in Federated Learning for Medical Image Classification
[article]
2023
arXiv
pre-print
The proliferation of deep learning applications in healthcare calls for data aggregation across various institutions, a practice often associated with significant privacy concerns. ...
This study addresses this need by integrating differential privacy, a leading privacy-preserving technique, into a federated learning framework for medical image classification. ...
While the study successfully addresses the need for privacy preservation in medical image analysis, it has a few limitations. ...
arXiv:2306.17794v1
fatcat:7e4nyr2gozghtejlb7hdp6f72q
Artificial Intelligence in Health in 2018: New Opportunities, Challenges, and Practical Implications
2019
IMIA Yearbook of Medical Informatics
Innovative training heuristics and encryption techniques may support distributed learning with preservation of privacy. ...
Conclusions: Performance of state-of-the-art AI machine learning algorithms can be enhanced by approaches that employ a multidisciplinary biomedical informatics pipeline to incorporate domain knowledge ...
, and incorporation of homomorphic encryption for privacy preservation [8] . ...
doi:10.1055/s-0039-1677925
pmid:31419815
pmcid:PMC6697508
fatcat:qhflemhlp5euvp5xmc4njd5pxq
Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
[article]
2020
arXiv
pre-print
Our proposed pipeline can be generalized to other privacy-sensitive medical data analysis problems. ...
In this work, we address the problem of multi-site fMRI classification with a privacy-preserving strategy. ...
then Algorithm 1 Privacy-preserving federated learning for multisite fMRI analysis Input: 1. ...
arXiv:2001.05647v3
fatcat:3ds65aoi7nablgo3rcfgwixsrq
Differential Privacy for Adaptive Weight Aggregation in Federated Tumor Segmentation
[article]
2023
arXiv
pre-print
This advancement is crucial for preserving the privacy of medical image data and safeguarding sensitive information. ...
To address these challenges, we present a differential privacy (DP) federated deep learning framework in medical image segmentation. ...
In this global differential privacy setup, privacy guarantees are adaptable and robust as the privacy budget and sensitivity can be tuned according to data, which is practical for privacy-preserving brain ...
arXiv:2308.00856v1
fatcat:tovep4u67bdn7ht3bk7vwjz2aa
Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
2022
ACM Transactions on Computing for Healthcare
Federated learning is the process of developing machine learning models over datasets distributed across data centers such as hospitals, clinical research labs, and mobile devices while preventing data ...
This paper aims to lay out existing research and list the possibilities of federated learning for healthcare industries. ...
Insuicient patient data makes it diicult to train deep learning models for medical applications, particularly for rare diseases. ...
doi:10.1145/3533708
fatcat:iktrdcf6vrdx5daupes2t4tove
Privacy-Preserving Serverless Edge Learning with Decentralized Small Data
[article]
2021
arXiv
pre-print
However, extensive data usages bring a new challenge or even threat to deep learning algorithms, i.e., privacy-preserving. ...
Distributed training strategies have recently become a promising approach to ensure data privacy when training deep models. ...
for those privacy-preserving algorithms to perform secure data exchanging. ...
arXiv:2111.14955v2
fatcat:cofiguye4fb4nm3fj7tpt7ghr4
Federated Learning in Real-Time Medical IoT: Optimizing Privacy and Accuracy for Chronic Disease Monitoring
2024
Journal of Electrical Systems
This study presents an innovative method called Adaptive Federated Learning for Chronic Disease Prediction (AFL-CDP), which is specifically designed for real-time medical Internet of Things (IoT) applications ...
In order to improve privacy in IoT devices with limited resources, the study integrates the utilization of SPECK, an advanced technique for preserving privacy. ...
world validation smart healthcare costs through fog computing Can et al.[16] Privacy- Wearable Federated deep Improved Increased preserving deep sensor data learning with accuracy and computational learning ...
doi:10.52783/jes.649
fatcat:np2uifi5tngtzmwfcjp5rqa46e
A Systematic Review of Federated Learning in the Healthcare Area: From the Perspective of Data Properties and Applications
2021
Applied Sciences
However, pooling the medical data into centralized storage to train a robust deep learning model faces privacy, ownership, and strict regulation challenges. ...
Excellent deep learning models are heavily data-driven. The more data trained, the more robust and more generalizable the performance of the deep learning model. ...
Furthermore, the authors express their gratitude to the anonymous reviewers for their comments and recommendations, which significantly improved the original work. ...
doi:10.3390/app112311191
fatcat:m6aq2o22cfbp5o3y4cgo7yk4au
Evaluating Optimal Differentially Private Learning - Shallow and Deep Techniques
2020
VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE
Hence privacy preserving analytics requires algorithmic techniques that can handle privacy, data quality and efficiency simultaneously. ...
Differential privacy is an algorithm that allows controlled machine learning practices for quality analytics. ...
Coupling the learning ability of deep learning with a robust privacy technique such as differential privacy provides a wide scope for efficient privacy preserving analytics in big data. Fig 1. ...
doi:10.35940/ijitee.j7456.0891020
fatcat:zbexmslo75ahlggc3ecptv575q
Evolutionary tree-based quasi identifier and federated gradient privacy preservations over big healthcare data
2022
International Journal of Power Electronics and Drive Systems (IJPEDS)
Next with the learnt quasi-identifiers, privacy preservation of data item is made by applying federated gradient arbitrary privacy preservation learning model. ...
This paper proposes a method called evolutionary tree-based quasi-identifier and federated gradient (ETQI-FD) for privacy preservations over big healthcare data. ...
A convolutional neural network (CNN) was customized for preserving the privacy via mapping [13] and deep learning [14] for recording electronic health sequences. ...
doi:10.11591/ijece.v12i1.pp903-913
fatcat:gqesekgqgjbjrhcsl2fxca7dui
Detecting Data Poisoning Attacks in Federated Learning for Healthcare Applications Using Deep Learning
2023
Iraqi Journal for Computer Science and Mathematics
The suggested solution detects and mitigates data poisoning attacks using deep learning and CNN architecture, specifically VGG16. ...
A robust strategy for spotting data poisoning threats in federated learning is presented in the study. ...
the VGG16-based deep learning model 2 Healthcare Institutions Collaborated 10 institutions Training Rounds 15 rounds Privacy Measures Secure and Privacy-Preserving Data Security Protected Sensitive Medical ...
doi:10.52866/ijcsm.2023.04.04.018
fatcat:yproxmq7bnbbxg46m62f3hia7e
Privacy-preserving Artificial Intelligence Techniques in Biomedicine
[article]
2020
arXiv
pre-print
As the most promising direction, we suggest combining federated machine learning as a more scalable approach with other additional privacy preserving techniques. ...
Hence, there has been a substantial effort to develop AI methods that can learn from sensitive data while protecting individuals' privacy. ...
JB's contribution was also supported by his VILLUM Young Investigator grant (nr. 13154).This paper reflects only the authors' view and the Commission is not responsible for any use that may be made of ...
arXiv:2007.11621v2
fatcat:qnmzqvqn5fgonjiwmudjlzwelm
Systematic Review of Privacy-Preserving Distributed Machine Learning From Federated Databases in Health Care
2020
JCO Clinical Cancer Informatics
Covered topics include (1) an introduction to privacy of patient data and distributed learning as a potential solution to preserving these data, a description of the legal context for patient data research ...
Distributed learning promises great potential to facilitate big data for medical application, in particular for international consortiums. ...
We used the search strings: "distributed learning," "distributed machine learning," and "privacy preserving data mining." ...
doi:10.1200/cci.19.00047
pmid:32134684
pmcid:PMC7113079
fatcat:rgfhzdm5fvetdclrpyyv3gsfty
« Previous
Showing results 1 — 15 out of 10,261 results