SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
Alexander Robey, Eric Wong, Hamed Hassani, George J. Pappas
Who it is from
University of Pennsylvaniaaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- Jailbreaking Black Box Large Language Models in Twenty QueriesUniversity of Pennsylvania · 1,871 citations
- Wonder3D: Single Image to 3D Using Cross-Domain DiffusionTexas A&M University · 987 citations
- Cultural bias and cultural alignment of large language modelsCornell University · 983 citations
- Respecting causality for training physics-informed neural networksUniversity of Pennsylvania · 911 citations
- BLINK: Multimodal Large Language Models Can See but Not PerceiveColumbia University · 848 citations
- Holodeck: Language Guided Generation of 3D Embodied AI EnvironmentsUniversity of Pennsylvania · 489 citations