Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Daniel Kang(International University of the Caribbean), Tatsunori Hashimoto(Massachusetts Institute of Technology), Matei Zaharia(University of California, Berkeley), Ion Stoica(University of California, Berkeley), Carlos Guestrin(Stanford University), Xuechen Li(University of Hong Kong)
Cited by 83
Related Papers
"Why Should I Trust You?"
|Unknown|2016|15.5k
Chord
|Unknown|2001|9.7k
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
|Unknown|2016|5.3k
Chord: a scalable peer-to-peer lookup protocol for internet applications
|IEEE/ACM Transactions on Networking|2003|3.1k
Cost-effective outbreak detection in networks
|Unknown|2007|2.5k