Skip to content
conftrace_

De Li

3 papers · 2026–2026 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Venues

AAAI (3)

Top co-authors

Hanbo Cai (1) Jia-Li Yin (1) Xiaolei Liu (1) Ying Luo (1) Xianxian Li (1) Jinyan Wang (1) Yan Xiao (1) Shouling Ji (1) Qiyu Li (1) Zhou Tan (1)

Research topics

Artificial Intelligence (2) Machine Learning (2) Core AI (2) Learning Types (2) Core Methods (1) Learning Paradigms (1)

Keywords

backdoor attack (2) graph learning (1) adversarial machine learning (1) speaker recognition (1) node classification (1) noisy label (1) amplitude modulation (1) semantic prototype (1) frequency modulation (1) audio security (1) domain skew (1) prototype-guided supervision (1) malicious association propagation (1) federated learning (1) local model isolation (1)

Papers

DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain Skew AAAI 2026 Modulation-Based Backdoors: Leveraging Amplitude and Frequency Patterns to Attack Speaker Recognition AAAI 2026 Prototype-Guided Supervision for Graph Learning with Noisy and Sparse Labels AAAI 2026