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

Xiaohu Du

3 indexed papers

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

Publications per year

3
26

Top categories

Crypto×3NLP×2AI×1Software Eng.×1

Frequent co-authors

Xinhao Deng3×
Yunhao Feng2×
Yifan Ding2×
Ming Wen2×
Yanming Guo2×
Yuxiang Xie2×

Research Timeline

2026
Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions

The paper introduces a multi-dimensional evasion framework and a new benchmark (A3S-Bench) to test autonomous agents, demonstrating that stateful, multi-turn attacks significantly increase system risk.

BraveGuard: From Open-World Threats to Safer Computer-Use Agents

BraveGuard is a self-evolving defense framework that improves the safety of computer-use agents by training guard models on open-world, multi-step threat trajectories rather than static benchmarks.

BraveGuard: From Open-World Threats to Safer Computer-Use Agents

BraveGuard is a self-evolving defense framework that significantly improves the safety monitoring of computer-use agents by generating guard model supervision from open-world threat discovery and realistic, multi-step execution trajectories.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.CLRecentMay 31, 2026

BraveGuard: From Open-World Threats to Safer Computer-Use Agents

Yunhao Feng, Yifan Ding, Xiaohu Du, Ming Wen +12 more

BraveGuard is a self-evolving defense framework that improves the safety of computer-use agents by training guard models on open-world, multi-step threat trajectories rather than static benchmarks.

View →
cs.CRcs.CLRecentMay 31, 2026

BraveGuard: From Open-World Threats to Safer Computer-Use Agents

Yunhao Feng, Xiaohu Du, Xinhao Deng, Yifan Ding +12 more

BraveGuard is a self-evolving defense framework that significantly improves the safety monitoring of computer-use agents by generating guard model supervision from open-world threat discovery and real…

View →
cs.CRcs.AIcs.SERecentMay 21, 2026

Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions

Jianan Ma, Xiaohu Du, Ruixiao Lin, Yaoxiang Bian +7 more

The paper introduces a multi-dimensional evasion framework and a new benchmark (A3S-Bench) to test autonomous agents, demonstrating that stateful, multi-turn attacks significantly increase system risk…

View →