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

Diyi Yang

2 indexed papers

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

Publications per year

2
26

Top categories

NLP×2Crypto×1Society×1

Frequent co-authors

Yuting Ning1×
Zhehao Zhang1×
Yash Kumar Lal1×
Boyu Gou1×
Junyi Li1×
Weitong Ruan1×

Research Timeline

2026
SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization

SecureForge is an automated pipeline that significantly reduces cybersecurity vulnerabilities in LLM-generated code by optimizing system prompts, achieving up to a 48% reduction in output vulnerabilities.

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

The paper introduces SkillHarm, a comprehensive benchmark and automated framework for evaluating skill-based attacks across the entire agent skill-use lifecycle, demonstrating that current agents remain highly vulnerable to both fixed-payload and self-mutating poisoning attacks.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentJun 1, 2026

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Yuting Ning, Zhehao Zhang, Yash Kumar Lal, Boyu Gou +7 more

The paper introduces SkillHarm, a comprehensive benchmark and automated framework for evaluating skill-based attacks across the entire agent skill-use lifecycle, demonstrating that current agents rema…

View →
cs.CRcs.CLcs.CYRecentMay 8, 2026

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization

Houjun Liu, Lisa Einstein, John Yang, Joachim Baumann +4 more

SecureForge is an automated pipeline that significantly reduces cybersecurity vulnerabilities in LLM-generated code by optimizing system prompts, achieving up to a 48% reduction in output vulnerabilit…

View →