Nicholas Carlini

ORCID：0000-0002-1463-3461

发表论文 158 篇 · 总被引 20757 次 · h-index 46

代表论文

• Code of "Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs" (2023 · arXiv (Cornell University) · 被引 196)
• Poisoning Web-Scale Training Datasets is Practical (2024 · 被引 119)
• Scalable Extraction of Training Data from (Production) Language Models (2023 · arXiv (Cornell University) · 被引 83)
• Identifying and Mitigating the Security Risks of Generative AI (2023 · Foundations and Trends® in Privacy and Security · 被引 55)
• Are aligned neural networks adversarially aligned? (2023 · arXiv (Cornell University) · 被引 25)
• SoK: Watermarking for AI-Generated Content (2025 · 被引 20)