amanda
amandasa
ยท
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially)
Safer Language Models
upvoted
a
paper
about 2 months ago
DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on
LLM-based Agent
updated
a Space
about 3 years ago
amandasa/TM-TKO-Model-UI