Cite
Notes
Only stored in your browser.
Attribution
Capability-Based Scaling Laws for LLM Red-Teaming
arXiv 2025
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
arXiv 2023
from 2 papers
Alexander Panfilov
Amin Karbasi
Anay Mehrotra
Blaine Nelson
Hyrum Anderson
Jonas Geiping
Maksym Andriushchenko
Manolis Zampetakis
Yaron Singer