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

Qingqing Ye

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2NLP×2AI×1ML×1

Frequent co-authors

Haibo Hu2×
Zi Liang1×
Ronghua Li1×
Yanyun Wang1×
Xiaoyu Xu1×
Minxin Du1×

Research Timeline

2026
When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents

The paper identifies 'unintended long-term state poisoning'—a security risk where routine user interactions gradually corrupt an LLM agent's persistent state—and proposes a defense mechanism called StateGuard.

Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection

This paper introduces Mobius Injection, a novel, lightweight attack that weaponizes autonomous LLM agents into zombie nodes to launch highly scalable AbO-DDoS attacks by exploiting a vulnerability called Semantic Closure.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLRecentMay 12, 2026

Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection

Zi Liang, Ronghua Li, Yanyun Wang, Qingqing Ye +1 more

This paper introduces Mobius Injection, a novel, lightweight attack that weaponizes autonomous LLM agents into zombie nodes to launch highly scalable AbO-DDoS attacks by exploiting a vulnerability cal…

View →
cs.CRcs.CLcs.LGRecentMay 7, 2026

When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents

Xiaoyu Xu, Minxin Du, Qipeng Xie, Haobin Ke +2 more

The paper identifies 'unintended long-term state poisoning'—a security risk where routine user interactions gradually corrupt an LLM agent's persistent state—and proposes a defense mechanism called St…

View →