arXiv:2501.07238
Roman Lutz
romanlutz
ยท
AI & ML interests
Responsible AI, AI Red Teaming
Recent Activity
upvoted
a
paper
about 1 month ago
Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
new activity
about 2 months ago
JailbreakV-28K/JailBreakV-28k:Cool dataset! Do we have a pure textual version jailbreaks provided?
authored
a paper
9 months ago
PyRIT: A Framework for Security Risk Identification and Red Teaming in
Generative AI System
Organizations
None yet
models
0
None public yet
datasets
0
None public yet