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

Fei Wu

3 indexed papers

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

Publications per year

3
26

Top categories

Crypto×2Comp. Eng.×1NLP×1

Frequent co-authors

Yang Yang1×
Guomin Yang1×
Yingjiu Li1×
Pengfei Wu1×
Rui Shi1×
Minming Huang1×

Research Timeline

2026
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

The paper introduces LITMUS, a novel benchmark that rigorously tests LLM agents for dangerous, physical-layer behavioral jailbreaks in real OS environments, revealing that current agents frequently execute high-risk operations despite safety guardrails.

To Wait or To Probe: Arbitrage Competition on High-Throughput Blockchains

The paper analyzes arbitrage competition on high-throughput blockchains, finding that while probabilistic search accounts for a small fraction of activity, it is disproportionately responsible for spam and gas consumption.

PriSrv+: Privacy and Usability-Enhanced Wireless Service Discovery with Fast and Expressive Matchmaking Encryption

The paper introduces PriSrv+, an advanced service discovery protocol that significantly enhances privacy, usability, and efficiency in wireless networks through a novel matchmaking encryption scheme called FEME.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentJun 4, 2026

PriSrv+: Privacy and Usability-Enhanced Wireless Service Discovery with Fast and Expressive Matchmaking Encryption

Yang Yang, Guomin Yang, Yingjiu Li, Pengfei Wu +5 more

The paper introduces PriSrv+, an advanced service discovery protocol that significantly enhances privacy, usability, and efficiency in wireless networks through a novel matchmaking encryption scheme c…

View →
cs.CERecentMay 30, 2026

To Wait or To Probe: Arbitrage Competition on High-Throughput Blockchains

Fei Wu, Burak Öz

The paper analyzes arbitrage competition on high-throughput blockchains, finding that while probabilistic search accounts for a small fraction of activity, it is disproportionately responsible for spa…

View →
cs.CRcs.CLRecentMay 11, 2026

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

Chiyu Zhang, Huiqin Yang, Bendong Jiang, Xiaolei Zhang +7 more

The paper introduces LITMUS, a novel benchmark that rigorously tests LLM agents for dangerous, physical-layer behavioral jailbreaks in real OS environments, revealing that current agents frequently ex…

View →