PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Paper
•
2402.15911
•
Published
•
1
Ashish Hooda
nunatak
AI & ML interests
None yet
Recent Activity
authored
a paper
about 16 hours ago
Invisible Perturbations: Physical Adversarial Examples Exploiting the
Rolling Shutter Effect
authored
a paper
about 18 hours ago
PRP: Propagating Universal Perturbations to Attack Large Language Model
Guard-Rails
commented on
a paper
about 18 hours ago
PRP: Propagating Universal Perturbations to Attack Large Language Model
Guard-Rails
Organizations
None yet
nunatak's activity
commented
a
paper
about 18 hours ago