Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2505.21556
Cited By
Benign-to-Toxic Jailbreaking: Inducing Harmful Responses from Harmless Prompts
26 May 2025
H. Kim
Minbeom Kim
Wonjun Lee
Kihyun Kim
Changick Kim
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"Benign-to-Toxic Jailbreaking: Inducing Harmful Responses from Harmless Prompts"
Title
No papers