Neil Zhenqiang Gong

Duke University — United States

Computer Science · Physical Sciences

48h-index7.8kcitations259works3.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Adversarial Robustness in Machine Learning(91), Privacy-Preserving Technologies in Data(72), Spam and Phishing Detection(30), Advanced Graph Neural Networks(28), Network Security and Intrusion Detection(27)

Publications259 total

ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
arXiv (Cornell University)·2025Open Access
PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features
arXiv (Cornell University)·2025Open Access
PromptLocate: Localizing Prompt Injection Attacks
arXiv (Cornell University)·2025Open Access
Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
2025· 1 citedOpen Access
Zero-Shot Autonomous Microscopy for Scalable and Intelligent Characterization of 2D Materials
ACS Nano·2025· 1 cited
EditTrack: Detecting and Attributing AI-assisted Image Editing
arXiv (Cornell University)·2025Open Access
WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
arXiv (Cornell University)·2025Open Access
Fingerprinting LLMs via Prompt Injection
arXiv (Cornell University)·2025Open Access
SecInfer: Preventing Prompt Injection via Inference-time Scaling
arXiv (Cornell University)·2025Open Access
A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives
arXiv (Cornell University)·2025Open Access
A Survey on Model Extraction Attacks and Defenses for Large Language Models
2025Open Access
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
arXiv (Cornell University)·2025Open Access
A Survey on Model Extraction Attacks and Defenses for Large Language Models
arXiv (Cornell University)·2025Open Access
BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
2025· 2 cited
Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
2025· 8 cited
Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework
ACM Transactions on Management Information Systems·2025Open Access
Safety at Scale: A Comprehensive Survey of Large Model Safety
SuperIntelligence - Robotics - Safety & Alignment·2025
VideoMarkBench: Benchmarking Robustness of Video Watermarking
arXiv (Cornell University)·2025Open Access
A Critical Evaluation of Defenses against Prompt Injection Attacks
arXiv (Cornell University)·2025Open Access
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
arXiv (Cornell University)·2025Open Access
page 1 of 13Next →

Frequent Co-authors

Binghui Wang(14), Jinyuan Jia(12), Xiaoyu Cao(10), Jinyuan Jia(9), Prateek Mittal(6), Emil Stefanov(5), Dawn Song(5), Minghong Fang(4), Zaixi Zhang(4), Ling Huang(4), Bin Liu(3), Jindong Wang(3), Xing Xie(3), Michael Backes(2), Eui Chul Richard Shin(2), Guolei Yang(2), Jia Liu(2), Ameet Talwalkar(2), Lester Mackey(2), Wenchang Xu(2)