Across 2M+ in-the-wild LLM conversations, jailbreak attempts show no higher complexity than normal chats, and assistant toxicity has declined over time, suggesting bounded attack sophistication.
9 com/datasets/dreadnode/aivillage-grt2 (2024), ac- cessed: 2025-06-05
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking
Across 2M+ in-the-wild LLM conversations, jailbreak attempts show no higher complexity than normal chats, and assistant toxicity has declined over time, suggesting bounded attack sophistication.