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

Fu Xiao

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×1Software Eng.×1

Frequent co-authors

Guoxin Lu1×
Letian Sha1×
Qing Wang1×
Peijie Sun1×
Hao Zhou1×
Hua Dai1×

Research Timeline

2026
MAS-SZZ: Multi-Agentic SZZ Algorithm for Vulnerability-Inducing Commit Identification

The paper proposes MAS-SZZ, a multi-agentic algorithm that significantly improves the identification of the earliest commit introducing a software vulnerability by combining root cause analysis with structured backward tracing.

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.CRcs.SERecentApr 27, 2026

MAS-SZZ: Multi-Agentic SZZ Algorithm for Vulnerability-Inducing Commit Identification

Sicong Cao, Jinxuan Xu, Le Yu, Jing Yang +3 more

The paper proposes MAS-SZZ, a multi-agentic algorithm that significantly improves the identification of the earliest commit introducing a software vulnerability by combining root cause analysis with s…

View →