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

Qin Wang

6 indexed papers

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

Publications per year

6
26

Top categories

Crypto×6Emerging Tech×3AI×2Software Eng.×1

Frequent co-authors

Minfeng Qi2×
Guangsheng Yu2×
Xu Wang2×
Zelin Li1×
Zhipeng Wang1×
Tianqing Zhu1×

Research Timeline

2026
Deanonymizing Bitcoin Transactions via Network Traffic Analysis with Semi-supervised Learning

The paper proposes NTSSL, a novel semi-supervised method that combines network traffic analysis and transaction clustering to significantly improve the deanonymization of Bitcoin transactions.

PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agents

PlanTwin introduces a privacy-preserving architecture that allows cloud-hosted LLMs to plan over sensitive local environments by projecting the raw state into a sanitized, abstract digital twin.

Clawed and Dangerous: Can We Trust Open Agentic Systems?

This paper systematizes the security challenges of open agentic systems, concluding that while attack characterization is mature, the field lacks robust guidelines for operational governance, memory integrity, and capability revocation.

DAO to (Anonymous) DAO Transactions

The paper introduces extsc{Dao$^2$}, a framework enabling secure, threshold-controlled payments from one Decentralized Autonomous Organization (DAO) to another, supporting both traceable and anonymous transfers.

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions

The paper introduces CAESAR, a novel multi-agent framework that coordinates LLM agents across five specialized roles to improve success rates and stability in complex, multi-stage cyber intrusion tasks.

Five Attacks on x402 Agentic Payment Protocol

This paper analyzes the x402 agentic payment protocol, demonstrating through five concrete, practical attacks that it is vulnerable across multiple stages of its payment workflow.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentMay 12, 2026

Five Attacks on x402 Agentic Payment Protocol

Zelin Li, Qin Wang, Zhipeng Wang

This paper analyzes the x402 agentic payment protocol, demonstrating through five concrete, practical attacks that it is vulnerable across multiple stages of its payment workflow.

View →
cs.CRRecentMay 9, 2026

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions

Minfeng Qi, Tianqing Zhu, Zijie Xu, Congcong Zhu +2 more

The paper introduces CAESAR, a novel multi-agent framework that coordinates LLM agents across five specialized roles to improve success rates and stability in complex, multi-stage cyber intrusion task…

View →
cs.CRcs.ETRecentApr 6, 2026

DAO to (Anonymous) DAO Transactions

Minfeng Qi, Lin Zhong, Qin Wang

The paper introduces extsc{Dao$^2$}, a framework enabling secure, threshold-controlled payments from one Decentralized Autonomous Organization (DAO) to another, supporting both traceable and anonymou…

View →
cs.CRcs.AIcs.ETRecentMar 27, 2026

Clawed and Dangerous: Can We Trust Open Agentic Systems?

Shiping Chen, Qin Wang, Guangsheng Yu, Xu Wang +1 more

This paper systematizes the security challenges of open agentic systems, concluding that while attack characterization is mature, the field lacks robust guidelines for operational governance, memory i…

View →
cs.CRcs.AIcs.ETRecentMar 19, 2026

PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agents

Guangsheng Yu, Qin Wang, Rui Lang, Shuai Su +1 more

PlanTwin introduces a privacy-preserving architecture that allows cloud-hosted LLMs to plan over sensitive local environments by projecting the raw state into a sanitized, abstract digital twin.

View →
cs.CRRecentMar 18, 2026

Deanonymizing Bitcoin Transactions via Network Traffic Analysis with Semi-supervised Learning

Shihan Zhang, Bing Han, Chuanyong Tian, Ruisheng Shi +2 more

The paper proposes NTSSL, a novel semi-supervised method that combines network traffic analysis and transaction clustering to significantly improve the deanonymization of Bitcoin transactions.

View →