133 citations · 281 across the 44 of their papers we have counts for
3 papers · 2 filters
Best-of-N Jailbreaking
John Hughes, Sara Price, Aengus Lynch +7
We introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variati…
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
Rylan Schaeffer, Dan Valentine, Luke Bailey +12
The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesir…
Investigating Data Contamination for Pre-training Language Models
Minhao Jiang, Ken Ziyu Liu, Ming Zhong +4
Language models pre-trained on web-scale corpora demonstrate impressive capabilities on diverse downstream tasks. However, there is increasing concern whether such capabilities mig…