Scholar
Dezhang Kong
Google Scholar ID: DMKe8qYAAAAJ
Zhejiang University
network security
AI security
AI agent
programmable networks
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
207
H-index
10
i10-index
10
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
12 items
Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems
2026
Cited
0
Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions
2026
Cited
0
AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
2026
Cited
0
Policy of Thoughts: Scaling LLM Reasoning via Test-time Policy Evolution
2026
Cited
0
MalURLBench: A Benchmark Evaluating Agents'Vulnerabilities When Processing Web URLs
2026
Cited
0
ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation
2026
Cited
1
DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection
2026
Cited
2
Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection
2025
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
