Dr. Qifeng Chen and MPhil Student Patrick Wan Received Best Paper Award at FTL-IJCAI 2021

CSE MPhil student Patrick Ching Pui Wan and his supervisor Dr. Qifeng Chen, Assistant Professor of Department of Computer Science & Engineering and Electronic & Computer Engineering, received the best paper award for their co-authored paper entitled "Robust Federated Learning with Attack-Adaptive Aggregation at International Workshop on Federated and Transfer Learning for Data Sparsity and Confidentiality in Conjunction with IJCAI 2021.

The award-winning paper suggested that federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks, even if some existing defense strategies are used. They proposed an attack-adaptive aggregation strategy to defend against various attacks for robust federated learning which is based on training a neural network with an attention mechanism that learns the vulnerability of federated learning models from a set of plausible attacks. Their approach has achieved competitive performance in defending model poisoning and backdoor attacks in federated learning tasks on image and text datasets.

International Joint Conferences on Artificial Intelligence Organization (IJCAI) is a non-profit corporation founded in California, in 1969 for scientific and educational purposes, including dissemination of information on Artificial Intelligence at conferences in which cutting-edge scientific results are presented and through dissemination of materials presented at these meetings in form of Proceedings, books, video recordings, and other educational materials. IJCAI conferences present premier international gatherings of AI researchers and practitioners and were held biennially in odd-numbered years since 1969. This year, the workshop was held on 21 August 2021.

Congratulations again to Dr. Chen and Patrick!

For more details, please refer to the workshop and their paper.

Best Paper Award received by Dr. Chen and Patrick

More News