DCInject: Persistent Backdoor Attacks via Frequency Manipulation in Personal Federated Learning

Authors: Nahom Birhan, Daniel Wesego, Dereje Shenkut et al.
Publication: ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Published: May 3, 2026
Source: Crossref
Back to Search View Original Cite This Article

Related Articles

Revisiting Backdoor Threat in Federated Instruction Tuning From a Signal Aggregation Perspective

Haodong Zhao, Jinming Hu et al. - May 2026

Read More
Inverse Rendering for High-Genus 3D Surface Meshes from Multi-View Images with Persistent Homology Priors

Xiang Gao, Xinmu Wang et al. - May 2026

Read More
MVP4EI: A Multi-View Persistent Spatio-Temporal Feature Learning for EEG Imputation

Guanjian Liu, Huan Liu et al. - May 2026

Read More
Exploiting Backdoor Trigger Towards Unlearnable Examples

Chun Li, Yuanchen Xun et al. - May 2026

Read More
BadLLM-TG: A Backdoor Defender Powered by LLM Trigger Generator

Ruyi Zhang, Heng Gao et al. - May 2026

Read More
Journal Ideas PyMinds Charcha More
PORE

About

About Us

Resources

Help Center Research Guides Citescore

Legal

Terms of Service Privacy Policy Cookie Policy Accessibility

Connect

Contact Us
© 2026 PORE. Content available under CC BY-NC 4.0