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

Mingzhe Li

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3AI×1Comp. Eng.×1

Frequent co-authors

Mingzhe Liu2×
Wenxin Tang1×
Wenbin Li1×
Junliang Liu1×
Jingyu Xiao1×
Xi Xiao1×

Research Timeline

2026
GasLiteAA: Optimizing ERC-4337 for Efficient and Secure Gas Sponsorship

GasLiteAA proposes optimizing the ERC-4337 standard by offloading gas sponsorship logic to Trusted Execution Environments (TEE), significantly reducing on-chain gas costs while maintaining security and verifiability.

Membership Inference Attacks on Vision-Language-Action Models

This paper presents the first systematic study of membership inference attacks (MIAs) against Vision-Language-Action (VLA) models, demonstrating that these models are highly vulnerable to privacy breaches even when only observing generated actions.

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

DCVD proposes a dual-channel cross-modal fusion framework that jointly detects software vulnerabilities and precisely localizes the vulnerable lines, outperforming existing state-of-the-art methods.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 10, 2026

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

Wenxin Tang, Wenbin Li, Junliang Liu, Jingyu Xiao +9 more

DCVD proposes a dual-channel cross-modal fusion framework that jointly detects software vulnerabilities and precisely localizes the vulnerable lines, outperforming existing state-of-the-art methods.

View →
cs.CRRecentMay 8, 2026

Membership Inference Attacks on Vision-Language-Action Models

Yuefeng Peng, Mingzhe Li, Kejing Xia, Renhao Zhang +1 more

This paper presents the first systematic study of membership inference attacks (MIAs) against Vision-Language-Action (VLA) models, demonstrating that these models are highly vulnerable to privacy brea…

View →
cs.CEcs.CRRecentApr 11, 2026

GasLiteAA: Optimizing ERC-4337 for Efficient and Secure Gas Sponsorship

Hongxu Su, Mingzhe Liu, Jie Xu, Xiaohua Jia +1 more

GasLiteAA proposes optimizing the ERC-4337 standard by offloading gas sponsorship logic to Trusted Execution Environments (TEE), significantly reducing on-chain gas costs while maintaining security an…

View →