{"id":4901,"date":"2023-07-14T16:58:58","date_gmt":"2023-07-14T08:58:58","guid":{"rendered":"https:\/\/inventec2.mjitec.tw\/?page_id=4901"},"modified":"2024-01-17T11:06:12","modified_gmt":"2024-01-17T03:06:12","slug":"fedtrust","status":"publish","type":"page","link":"https:\/\/inventec2.mjitec.tw\/en\/ai\/fedtrust\/","title":{"rendered":"FedTrust"},"content":{"rendered":"

[vc_row full_width=”stretch_row”][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[vc_row_inner el_class=”md-full-col”][vc_column_inner el_class=”m_p” width=”1\/2″]\n
\n \t
\n \t\t\n\t \n\t

FedTrust: Towards Building
\nSecure Robust and Trustworthy Moderators for Federated Learning <\/h2>\n\t <\/div><\/div>[vc_column_text css=”.vc_custom_1689325188509{margin-bottom: 20px !important;}”]<\/p>\n
\n

IEEE International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR 2021)<\/p>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1689327011743{margin-bottom: 5px !important;}”]<\/p>\n

\n
Authors<\/h6>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1689325197392{margin-bottom: 20px !important;}”]<\/p>\n

\n

Chih-Fan Hsu, Jing-Lun Huang, Feng-Hao Liu, Ming-Ching Chang, and Wei-Chao Chen<\/p>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1689327021247{margin-bottom: 5px !important;}”]<\/p>\n

\n
Published<\/h6>\n<\/div>\n

[\/vc_column_text][vc_column_text]<\/p>\n

\n

2022\/9\/8<\/p>\n<\/div>\n

[\/vc_column_text][\/vc_column_inner][vc_column_inner el_class=”m_p” width=”1\/2″][vc_single_image image=”5044″ img_size=”full”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=”stretch_row”][vc_column][vc_row_inner content_placement=”top” css=”.vc_custom_1657794580528{margin-bottom: 20px !important;}”][vc_column_inner el_class=”m_p paragraph_title” width=”1\/3″]\n
\n \t
\n \t\t\n\t \n\t

Abstract <\/h2>\n\t <\/div><\/div>[\/vc_column_inner][vc_column_inner el_class=”m_p” width=”2\/3″][vc_column_text]Most Federated Learning (FL) systems are built upon a strong assumption of trust—clients fully trust the centralized moderator, which might not be feasible in practice.
\nThis work aims to mitigate the assumption by using appropriate cryptographic tools.
\nParticularly, we examine various scenarios with different trust demands in FL, and then design the corresponding practical protocols with lightweight cryptographic tools.
\nThree solutions for secure and trustworthy aggregation are proposed with increasing sophistication: (1) a single verifiable moderator, (2) a single secure and verifiable moderator, and (3) multiple secure and verifiable moderators, which can handle adversarial behaviors with different levels.
\nWe evaluate the performances of all our proposed protocols on the test accuracy and the training time, showing that our protocols maintain the accuracy with time overhead from 30% to 156% depending on the secure and trustworthy levels. The protocols can be deployed in many practical FL settings with appropriate optimizations.[\/vc_column_text][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]
\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row][vc_column width=”1\/3″ el_class=”m_p keyword_title”][vc_column_text]<\/p>\n

Keywords<\/h2>\n

[\/vc_column_text][\/vc_column][vc_column width=”2\/3″ el_class=”m_p keyword”][vc_row_inner content_placement=”middle”][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VGZWRlcmF0ZWQlMjBMZWFybmluZyUzQyUyRmxpJTNFJTBBJTNDJTJGdWwlM0U=[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VNdWx0aS1QYXJ0eSUyMENvbXB1dGF0aW9uJTNDJTJGbGklM0UlMEElM0MlMkZ1bCUzRQ==[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VIb21vbW9ycGhpYyUyMEVuY3J5cHRpb24lM0MlMkZsaSUzRSUwQSUzQyUyRnVsJTNF[\/vc_raw_html][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=”stretch_row” el_class=”bg” css=”.vc_custom_1657248474326{padding-top: 50px !important;padding-bottom: 50px !important;}”][vc_column][vc_column_text css=”.vc_custom_1689327063310{margin-bottom: 20px !important;}”]<\/p>\n

Download<\/h3>\n

[\/vc_column_text][vc_row_inner content_placement=”middle”][vc_column_inner el_class=”download_btn_wrap”][vc_btn title=”PDF” style=”flat” color=”white” align=”center” link=”url:https%3A%2F%2Fieeexplore.ieee.org%2Fdocument%2F9874673|target:_blank” el_class=”download_btn”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row]<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"

[vc_row full_width=”stretch_row”][vc_column][vc_row_inner el_class=”md-full-col”][vc_column_inner el_class=”m_p” width=”1\/2″][vc_column_text css=”.vc_custom_1689325188509{margin-bottom: 20px !important;}”] IEEE International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR 2021) [\/vc_column_text][vc_column_text css=”.vc_custom_1689327011743{margin-bottom: 5px !important;}”] Authors [\/vc_column_text][vc_column_text css=”.vc_custom_1689325197392{margin-bottom: 20px !important;}”] Chih-Fan Hsu, Jing-Lun Huang, Feng-Hao Liu, Ming-Ching Chang, and Wei-Chao Chen [\/vc_column_text][vc_column_text css=”.vc_custom_1689327021247{margin-bottom: 5px !important;}”] Published [\/vc_column_text][vc_column_text] 2022\/9\/8 [\/vc_column_text][\/vc_column_inner][vc_column_inner el_class=”m_p” width=”1\/2″][vc_single_image image=”5044″ img_size=”full”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column][\/vc_column][\/vc_row][vc_row full_width=”stretch_row”][vc_column][vc_row_inner content_placement=”top” css=”.vc_custom_1657794580528{margin-bottom:…<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":4975,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-4901","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/4901","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/comments?post=4901"}],"version-history":[{"count":0,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/4901\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/4975"}],"wp:attachment":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/media?parent=4901"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}