Get started
Author

Ning Zhang

Observed name: Zhang, Ning
OpenAlex ID: A5134978311
MechAudit-40: White-Box Auditing across 40 LLM Attack Mechanisms
2026 · Guo, Zhen, Shi, Shanghao, et al. · arXiv (Cornell University)
PDF
From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning
2026 · Shi, Shanghao, Zhang, Chaoyu, et al. · arXiv (Cornell University)
PDF
Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning
2026 · Shi, Shanghao, Wang, Xiao, et al. · arXiv (Cornell University)
PDF
AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents
2026 · Ma, Xinhang, Li, Taoran, et al. · arXiv (Cornell University)
PDF
Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization
2026 · Yu, Hexuan, Zhang, Chaoyu, et al. · arXiv (Cornell University)
PDF
Protecting Language Models Against Unauthorized Distillation through Trace Rewriting
2026 · Association for Computational Linguistics 2026, Ma, Xinhang, et al. · Underline Science Inc.
Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
2026 · Association for Computational Linguistics 2026, Hua, Peichun, et al. · Underline Science Inc.
MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons
2026 · Gong, Kehong, Wen, Zhengyu, et al. · arXiv (Cornell University)
PDF
Low Rank Adaptation for Adversarial Perturbation
2026 · Liu, Han, Shi, Shanghao, et al. · arXiv (Cornell University)
PDF
Works count: 9
Citation count:
H-index:
I10-index:
Year
Topic
Type