"au:"Nicholas Carlini"" — arXiv2 Search

/ Date/ Name

/ Date/ Name

"au:"Nicholas Carlini"" — arXiv2 Search

Showing 1–7 of 7 results

/ Date/ Name

Jan 17, 2026Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces Oct 8, 2025Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples Feb 4, 2025Adversarial ML Problems Are Getting Harder to Solve and to Evaluate Nov 15, 2024Measuring Non-Adversarial Reproduction of Training Data in Large Language Models Oct 17, 2024Persistent Pre-Training Poisoning of LLMs Jun 17, 2024Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI Jul 12, 2019Stateful Detection of Black-Box Adversarial Attacks