Xiangzheng Zhang
Scholar

Xiangzheng Zhang

Google Scholar ID: da0Y7jUAAAAJ
360
AI safetyLarge language modelsInformation Retrieval
Google Scholar↗
Citations & Impact
All-time
Citations
136
 
H-index
5
 
i10-index
3
 
Publications
10
 
Co-authors
4
list available
Contact
No contact links provided.
Publications
35 items
Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
2026
Cited
0
MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
2026
Cited
0
DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs
2026
Cited
0
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
2026
Cited
0
Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
2026
Cited
0
TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
2026
Cited
0
When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
2026
Cited
0
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
2026
Cited
0
Resume (English only)
Co-authors
4 total
Haosheng Zou
Haosheng Zou
Tsinghua University
Lin Sun
Lin Sun
Qihoo 360
Guangxiang Zhao
Guangxiang Zhao
Peking University
Shousheng Jia
Shousheng Jia
360