Search Results for author: Dazhong Rong

Found 4 papers, 2 papers with code

Clean-image Backdoor Attacks

no code implementations22 Mar 2024 Dazhong Rong, Guoyao Yu, Shuheng Shen, Xinyi Fu, Peng Qian, Jianhai Chen, Qinming He, Xing Fu, Weiqiang Wang

To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data.

Fairness Image Classification

CoMeta: Enhancing Meta Embeddings with Collaborative Information in Cold-start Problem of Recommendation

no code implementations14 Mar 2023 Haonan Hu, Dazhong Rong, Jianhai Chen, Qinming He, Zhenguang Liu

Specifically, for a new item: B-EG calculates the similarity-based weighted sum of the ID embeddings of old items as its base embedding; S-EG generates its shift embedding not only with its attribute features but also with the average ID embedding of the users who interacted with it.

Attribute Meta-Learning

Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios

1 code implementation26 Apr 2022 Dazhong Rong, Qinming He, Jianhai Chen

Various attack methods against recommender systems have been proposed in the past years, and the security issues of recommender systems have drawn considerable attention.

Federated Learning Recommendation Systems

FedRecAttack: Model Poisoning Attack to Federated Recommendation

1 code implementation1 Apr 2022 Dazhong Rong, Shuai Ye, Ruoyan Zhao, Hon Ning Yuen, Jianhai Chen, Qinming He

Experimental results demonstrate that our proposed FedRecAttack achieves the state-of-the-art effectiveness while its side effects are negligible.

Federated Learning Model Poisoning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.