Abstract
Abstract—Federated learning is a distributed machine learning paradigm that enables multiple actors to collaboratively train a common model without sharing their local data, thus addressing data privacy issues, especially in sensitive domains such as healthcare. However, federated learning is vulnerable to poisoning attacks, where malicious (Byzantine) clients can manipulate their local updates to degrade the performance or compromise the
privacy of the global model. To mitigate this problem, this paper proposes a novel method that reduces the influence of malicious clients based on their confidence. We evaluate our method on the Retinal OCT dataset consisting of age-related macular degeneration and diabetic macular edema, using InceptionV3 and VGG19 architecture. The proposed technique significantly improves the global model’s precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC-ROC) for both InceptionV3 and VGG19. For InceptionV3, precision rises from 0.869 to 0.906, recall rises from 0.836 to 0.889, and F1 score
rises from 0.852 to 0.898. For VGG19, precision rises from 0.958 to 0.963, recall rises from 0.917 to 0.941, and F1 score rises from 0.937 to 0.952.
Index Terms—Computer Vision, Federated learning, Deep Learning, Medical Image Processing, Data poisoning, Retinal OCT
privacy of the global model. To mitigate this problem, this paper proposes a novel method that reduces the influence of malicious clients based on their confidence. We evaluate our method on the Retinal OCT dataset consisting of age-related macular degeneration and diabetic macular edema, using InceptionV3 and VGG19 architecture. The proposed technique significantly improves the global model’s precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC-ROC) for both InceptionV3 and VGG19. For InceptionV3, precision rises from 0.869 to 0.906, recall rises from 0.836 to 0.889, and F1 score
rises from 0.852 to 0.898. For VGG19, precision rises from 0.958 to 0.963, recall rises from 0.917 to 0.941, and F1 score rises from 0.937 to 0.952.
Index Terms—Computer Vision, Federated learning, Deep Learning, Medical Image Processing, Data poisoning, Retinal OCT
| Original language | English |
|---|---|
| Title of host publication | 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA) |
| Place of Publication | United States |
| Publisher | IEEE |
| Pages | 81-88 |
| Number of pages | 8 |
| ISBN (Electronic) | 9798350382204 |
| ISBN (Print) | 9798350382211 (Print on demand) |
| DOIs | |
| Publication status | Published - 2023 |
| Event | The International Conference on Digital Image Computing: Techniques and Applications: DICTA 2023 - Sails Port Macquarie, Port Macquarie, Australia Duration: 28 Nov 2023 → 01 Dec 2023 https://www.dictaconference.org/ https://www.dictaconference.org/?page_id=2623 (Conference program) |
Publication series
| Name | Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA) |
|---|---|
| Publisher | IEEE |
Conference
| Conference | The International Conference on Digital Image Computing: Techniques and Applications |
|---|---|
| Country/Territory | Australia |
| City | Port Macquarie |
| Period | 28/11/23 → 01/12/23 |
| Other | Digital Image Computing: Techniques and Applications (DICTA) is the main Australian Conference on computer vision, image processing, pattern recognition, and related areas. DICTA was established in 1991 as the premier conference of the Australian Pattern Recognition Society (APRS). DICTA provides a forum for researchers, engineers, and practitioners to present their latest findings and innovations in these areas, as well as to exchange ideas and discuss emerging trends and challenges in the field. The conference covers a wide range of topics, including image and video processing, machine learning, pattern recognition, and computer graphics, among others. |
| Internet address |
|