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

Yingjie Zhang

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

Yuanbo Xie2×
Yulin Li2×
Liya Su2×
Tingwen Liu2×
Tianyun Liu1×
Suchen Liu1×

Research Timeline

2026
Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game

The paper introduces CanaryRAG, a novel dual-path runtime defense mechanism that detects RAG Knowledge Base Leakage attacks by embedding canary tokens into retrieved knowledge chunks.

What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems

The paper introduces and analyzes cross-session stored prompt injection, demonstrating that persistent system state transforms prompt injection from a temporary model-level threat into a long-lived, system-level vulnerability in agentic systems.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentJun 3, 2026

What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems

Yuanbo Xie, Tianyun Liu, Yingjie Zhang, Suchen Liu +3 more

The paper introduces and analyzes cross-session stored prompt injection, demonstrating that persistent system state transforms prompt injection from a temporary model-level threat into a long-lived, s…

View →
cs.CRcs.AIcs.CLRecentApr 12, 2026

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game

Yuanbo Xie, Yingjie Zhang, Yulin Li, Shouyou Song +4 more

The paper introduces CanaryRAG, a novel dual-path runtime defense mechanism that detects RAG Knowledge Base Leakage attacks by embedding canary tokens into retrieved knowledge chunks.

View →