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

Hua Dai

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2AI×1NLP×1

Frequent co-authors

Hao Zhou2×
Guoxin Lu1×
Letian Sha1×
Qing Wang1×
Peijie Sun1×
Fu Xiao1×

Research Timeline

2026
PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning

The paper proposes PAC-DP, a personalized adaptive clipping framework that dynamically adjusts gradient clipping thresholds based on the desired privacy budget, significantly improving the privacy-utility trade-off in federated learning.

Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks

The paper introduces Safety Bottleneck Regularization (SBR), a novel defense mechanism that anchors LLM safety by constraining the unembedding layer, effectively preventing harmful fine-tuning (HFT) even when other defenses fail.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLRecentMay 7, 2026

Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks

Guoxin Lu, Letian Sha, Qing Wang, Peijie Sun +3 more

The paper introduces Safety Bottleneck Regularization (SBR), a novel defense mechanism that anchors LLM safety by constraining the unembedding layer, effectively preventing harmful fine-tuning (HFT) e…

View →
cs.CRRecentMar 25, 2026

PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning

Hao Zhou, Siqi Cai, Hua Dai, Geng Yang +2 more

The paper proposes PAC-DP, a personalized adaptive clipping framework that dynamically adjusts gradient clipping thresholds based on the desired privacy budget, significantly improving the privacy-uti…

View →