Annual Computer Security Applications ConferenceJun 27, 2024
For this #ThrowbackThursday, we will look at #ACSAC2023's Trustworthy Machine Learning session. The links in this thread will lead you to the paper pdfs and the slide decks, so be sure to check them out! 1/5
Show threadAnnual Computer Security Applications Conference
The first paper in this session was Zhuang et al.'s "DeepContract: Controllable Authorization of Deep Learning Models" which presents a new approach to secure and manage deep learning model access. (https://www.acsac.org/2023/program/final/s10.html) 2/5
#DeepLearning #ML SecurityInML
ACSAC2023 Program – powered by OpenConf

Jun 27, 2024 at 2:00pmWeb
Show threadAnnual Computer Security Applications ConferenceJun 27, 2024
The second paper in this session was Li et al.'s "Secure MLaaS with Temper: Trusted and Efficient Model Partitioning and Enclave Reuse" which discusses enhancing MLaaS security and efficiency. (https://www.acsac.org/2023/program/final/s172.html) 3/5
#MLaaS #SecurityInML #EfficencyInML
ACSAC2023 Program – powered by OpenConf

Show threadAnnual Computer Security Applications ConferenceJun 27, 2024
The third paper in this session was Cui & Mei's "ABFL: A Blockchain-enabled Robust Framework for Secure and Trustworthy Federated Learning" which discusses a resilient architecture combining #blockchain and #FederatedLearning. (https://www.acsac.org/2023/program/final/s133.html) 4/5
ACSAC2023 Program – powered by OpenConf

Show threadAnnual Computer Security Applications ConferenceJun 27, 2024
The final paper in this session was Castillo et al.'s "FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attacks" which presented a novel approach to enhance #FederatedLearning #Security. (https://www.acsac.org/2023/program/final/s265.html) 5/5
ACSAC2023 Program – powered by OpenConf