firstbacksecondback
2 Results
|
Poster
|
Fri 16:30 |
Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters Haibo Jin · Andy Zhou · Joe Menke · Haohan Wang |
|
|
Workshop
|
Decompose, Recompose, and Conquer: Multi-modal LLMs are Vulnerable to Compositional Adversarial Attacks in Multi-Image Queries Julius Broomfield · George Ingebretsen · Reihaneh Iranmanesh · Sara Pieri · Ethan Kosak-Hine · Tom Gibbs · Reihaneh Rabbany · Kellin Pelrine |