Nicholas Carlini
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
arXiv 2026
Defeating Prompt Injections by Design
arXiv 2025
Forcing Diffuse Distributions out of Language Models
arXiv 2024
On Evaluating the Durability of Safeguards for Open-Weight LLMs
arXiv 2024
Universal and Transferable Adversarial Attacks on Aligned Language Models
arXiv 2023
Effective Prompt Extraction from Language Models
arXiv 2023
Evading Black-box Classifiers Without Breaking Eggs
arXiv 2023
Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems
arXiv 2022
Deduplicating Training Data Makes Language Models Better
ACL 2022 5
Extracting Training Data from Large Language Models
arXiv 2020
Affiliations
Frequent co-authors
10from 10 papers