ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
Paper • 2509.25843 • Published • 19
Korea University
university
AI & ML interests
None defined yet.
Recent Activity
Papers
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
P-YI
submitted a
paper to Daily Papers 4 days ago