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

Qi Zhao

3 indexed papers

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

Publications per year

3
26

Top categories

AI×2Crypto×2ML×1Vision×1Info Retrieval×1

Frequent co-authors

Zilin Du1×
Junqi Zhao1×
Boyang Albert Li1×
Safayat Bin Hakim1×
Aniqa Afzal1×
Vigna Majmundar1×

Research Timeline

2026
Breaking Euston: Recovering Private Inputs from Secure Inference by Exploiting Subspace Leakage

This paper demonstrates that the Euston secure inference framework, which uses SVD-based matrix transmission to save bandwidth, leaks private input data by exploiting subspace leakage of random masks.

CyberCane: Neuro-Symbolic RAG for Privacy-Preserving Phishing Detection with Formal Ontology Reasoning

CyberCane is a neuro-symbolic framework that enhances phishing detection by combining symbolic rule analysis with privacy-preserving RAG and formal ontology reasoning, achieving high recall against AI-generated threats while maintaining strict data privacy.

On the Difficulty of Learning a Meta-network for Training Data Selection

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve data selection accuracy.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CVRecentMay 30, 2026

On the Difficulty of Learning a Meta-network for Training Data Selection

Zilin Du, Junqi Zhao, Boyang Albert Li

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…

View →
cs.CRcs.AIcs.IRRecentApr 26, 2026

CyberCane: Neuro-Symbolic RAG for Privacy-Preserving Phishing Detection with Formal Ontology Reasoning

Safayat Bin Hakim, Aniqa Afzal, Qi Zhao, Vigna Majmundar +2 more

CyberCane is a neuro-symbolic framework that enhances phishing detection by combining symbolic rule analysis with privacy-preserving RAG and formal ontology reasoning, achieving high recall against AI…

View →
cs.CRRecentApr 19, 2026

Breaking Euston: Recovering Private Inputs from Secure Inference by Exploiting Subspace Leakage

Jiaqi Zhao, Fengwei Wang

This paper demonstrates that the Euston secure inference framework, which uses SVD-based matrix transmission to save bandwidth, leaks private input data by exploiting subspace leakage of random masks.

View →