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

Jinyuan Jia

6 indexed papers

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

Publications per year

6
26

Top categories

Crypto×6ML×2AI×1NLP×1

Frequent co-authors

Yanting Wang4×
Wei Zou2×
Chenlong Yin2×
Ying Chen2×
Runpeng Geng2×
Weifei Jin1×

Research Timeline

2026
EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method

The paper introduces EnsembleSHAP, a novel, computationally efficient, and provably robust feature attribution method specifically designed for the Random Subspace Method to provide secure explanations.

AgentWatcher: A Rule-based Prompt Injection Monitor

AgentWatcher is a novel, rule-based monitor designed to detect prompt injection attacks in LLM agents by focusing detection on causally influential context segments, thereby improving scalability and explainability.

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

The paper introduces TRUSTDESC, a novel framework that prevents tool poisoning attacks in LLM applications by automatically generating highly accurate and trusted tool descriptions directly from the tool's source code and behavior.

PIArena: A Platform for Prompt Injection Evaluation

The paper introduces PIArena, a unified and extensible platform designed to address the lack of standardized evaluation for prompt injection, revealing critical limitations in current state-of-the-art defenses.

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption

The paper introduces FlashRT, a novel framework that significantly improves the computational and memory efficiency of optimization-based red-teaming attacks against long-context LLMs, enabling systematic security evaluation at scale.

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

CleanBase is a method that detects malicious documents in RAG knowledge databases by identifying clusters (cliques) of documents that exhibit unusually high semantic similarity.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGRecentMay 1, 2026

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

Weifei Jin, Xilong Wang, Wei Zou, Jinyuan Jia +1 more

CleanBase is a method that detects malicious documents in RAG knowledge databases by identifying clusters (cliques) of documents that exhibit unusually high semantic similarity.

View →
cs.CRRecentApr 30, 2026

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption

Yanting Wang, Chenlong Yin, Ying Chen, Jinyuan Jia

The paper introduces FlashRT, a novel framework that significantly improves the computational and memory efficiency of optimization-based red-teaming attacks against long-context LLMs, enabling system…

View →
cs.CRcs.AIcs.CLRecentApr 9, 2026

PIArena: A Platform for Prompt Injection Evaluation

Runpeng Geng, Chenlong Yin, Yanting Wang, Ying Chen +1 more

The paper introduces PIArena, a unified and extensible platform designed to address the lack of standardized evaluation for prompt injection, revealing critical limitations in current state-of-the-art…

View →
cs.CRRecentApr 8, 2026

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Hengkai Ye, Zhechang Zhang, Jinyuan Jia, Hong Hu

The paper introduces TRUSTDESC, a novel framework that prevents tool poisoning attacks in LLM applications by automatically generating highly accurate and trusted tool descriptions directly from the t…

View →
cs.CRRecentApr 1, 2026

AgentWatcher: A Rule-based Prompt Injection Monitor

Yanting Wang, Wei Zou, Runpeng Geng, Jinyuan Jia

AgentWatcher is a novel, rule-based monitor designed to detect prompt injection attacks in LLM agents by focusing detection on causally influential context segments, thereby improving scalability and…

View →
cs.CRRecentMar 31, 2026

EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method

Yanting Wang, Jinyuan Jia

The paper introduces EnsembleSHAP, a novel, computationally efficient, and provably robust feature attribution method specifically designed for the Random Subspace Method to provide secure explanation…

View →