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

Wei Ding

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2AI×2NLP×1

Frequent co-authors

Yutong Cheng1×
Changze Li1×
Raihan Sultan Pasha Basuki1×
Qian Cui1×
Peng Gao1×
Xuwei Ding1×

Research Timeline

2026
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

The paper introduces OS-BLIND, a benchmark demonstrating that current safety evaluations fail to detect critical vulnerabilities in computer-use agents when user instructions are benign, showing high attack success rates even for safety-aligned models.

TTPrint: Evidence-Grounded TTP Extraction via Diverge-then-Converge Verification

TTPrint proposes a novel diverge-then-converge framework for extracting MITRE ATT&CK techniques from CTI reports, significantly improving both recall and precision compared to existing methods.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLRecentMay 25, 2026

TTPrint: Evidence-Grounded TTP Extraction via Diverge-then-Converge Verification

Yutong Cheng, Changze Li, Raihan Sultan Pasha Basuki, Qian Cui +2 more

TTPrint proposes a novel diverge-then-converge framework for extracting MITRE ATT&CK techniques from CTI reports, significantly improving both recall and precision compared to existing methods.

View →
cs.CRcs.AIRecentApr 12, 2026

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Xuwei Ding, Skylar Zhai, Linxin Song, Jiate Li +5 more

The paper introduces OS-BLIND, a benchmark demonstrating that current safety evaluations fail to detect critical vulnerabilities in computer-use agents when user instructions are benign, showing high…

View →