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

Hao Pei

3 indexed papers

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

Publications per year

3
26

Top categories

Crypto×3AI×2ML×1Networking×1Software Eng.×1

Frequent co-authors

Shichao Pei2×
Annan Fu1×
Maryam Tanha1×
Guanjie Lin1×
Yinxin Wan1×
Ting Xu1×

Research Timeline

2026
Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use

This paper introduces Back-Reveal, an attack demonstrating that backdoored LLM agents can systematically exfiltrate sensitive user data by embedding semantic triggers into tool-use mechanisms.

Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways

The paper introduces GateScope, a black-box framework that audits commercial LLM API gateways, revealing frequent discrepancies in model behavior, billing, and performance across real-world services.

Self-Supervised Learning for Android Malware Detection on a Time-Stamped Dataset

The paper proposes a time-aware self-supervised learning framework using BYOL to improve Android malware detection robustness by accurately accounting for app release times.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGRecentApr 24, 2026

Self-Supervised Learning for Android Malware Detection on a Time-Stamped Dataset

Annan Fu, Hao Pei, Maryam Tanha

The paper proposes a time-aware self-supervised learning framework using BYOL to improve Android malware detection robustness by accurately accounting for app release times.

View →
cs.CRcs.AIcs.NIRecentApr 22, 2026

Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways

Guanjie Lin, Yinxin Wan, Shichao Pei, Ting Xu +2 more

The paper introduces GateScope, a black-box framework that audits commercial LLM API gateways, revealing frequent discrepancies in model behavior, billing, and performance across real-world services.

View →
cs.CRcs.AIRecentApr 7, 2026

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use

Wuyang Zhang, Shichao Pei

This paper introduces Back-Reveal, an attack demonstrating that backdoored LLM agents can systematically exfiltrate sensitive user data by embedding semantic triggers into tool-use mechanisms.

View →