Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Daoqiang Zhang

Daoqiang Zhang

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3Crypto×2ML×1

Frequent co-authors

Qi Zhu3×
Yinbo Yu2×
Jing Fang2×
Chunwei Tian2×
Jiajia Liu2×
Deyu Zhuang1×

Research Timeline

2026
Fast and Lightweight Backdoor Detection via Head Random Probing

The paper proposes HTell, a fast and lightweight data-free backdoor detector that analyzes the abnormal response concentration of backdoored models on the target class using random latent probes applied directly to the prediction head.

Lightweight and Fast Backdoor Model Detection

The paper proposes DFBScanner, a lightweight static parameter inspection framework that detects backdoor attacks by analyzing anomalous parameter updates in the final classification layer, achieving fast and generalizable detection.

Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations

The paper proposes PC-MambaSDE, a physically-constrained continuous-time framework that accurately predicts Remaining Useful Life (RUL) despite irregular sensor observations and ensures physically plausible degradation trajectories.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations

Deyu Zhuang, Peiliang Gong, Yang Shao, Liyuan Shu +3 more

The paper proposes PC-MambaSDE, a physically-constrained continuous-time framework that accurately predicts Remaining Useful Life (RUL) despite irregular sensor observations and ensures physically pla…

View →
cs.CRcs.AIcs.LGRecentMay 17, 2026

Fast and Lightweight Backdoor Detection via Head Random Probing

Yinbo Yu, Xueyu Yin, Jing Fang, Chunwei Tian +3 more

The paper proposes HTell, a fast and lightweight data-free backdoor detector that analyzes the abnormal response concentration of backdoored models on the target class using random latent probes appli…

View →
cs.CRcs.AIRecentMay 17, 2026

Lightweight and Fast Backdoor Model Detection

Yinbo Yu, Jing Fang, Xuewen Zhang, Chunwei Tian +3 more

The paper proposes DFBScanner, a lightweight static parameter inspection framework that detects backdoor attacks by analyzing anomalous parameter updates in the final classification layer, achieving f…

View →