Skip to main content

Filter articles by Type to Filter.

Skip filters and go to articles.

16 articles displayed.

Researchers' adversarial prompts can elicit arbitrary harmful behaviors from state-of-the-art commercial LLMs with high probability, demonstrating potentials for misuse.
Friday, July 28, 2023
view looking downstreet as vehicles and pedestrians are glowing green
Wednesday, July 26, 2023
Tuesday, July 25, 2023
Matt A. Smith
Tuesday, July 25, 2023
Two people walking between machinery
Thursday, July 20, 2023
NSF Logo
Wednesday, July 19, 2023
Professor Yuvraj Agarwal
Tuesday, July 18, 2023
Moisés Padilla
Tuesday, July 18, 2023
A woman working at a lab table with children on either side
Tuesday, July 18, 2023
Anthony Carrigan
Friday, July 14, 2023
Joanna Bosse
Friday, July 14, 2023
Thursday, July 13, 2023