Výsledky vyhledávání - "Bailey, Luke"

Report

When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?

Autor: Schaeffer, Rylan, Valentine, Dan, Bailey, Luke, Chua, James, Eyzaguirre, Cristóbal, Durante, Zane, Benton, Joe, Miranda, Brando, Sleight, Henry, Hughes, John, Agrawal, Rajashree, Sharma, Mrinank, Emmons, Scott, Koyejo, Sanmi, Perez, Ethan

The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of vision-languag

Externí odkaz: http://arxiv.org/abs/2407.15211

Zobrazit plný text záznamu

Report

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

Autor: Toyer, Sam, Watkins, Olivia, Mendes, Ethan Adrian, Svegliato, Justin, Bailey, Luke, Wang, Tiffany, Ong, Isaac, Elmaaroufi, Karim, Abbeel, Pieter, Darrell, Trevor, Ritter, Alan, Russell, Stuart

While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable to prompt injection attacks: malicious third party prompts that subvert the intent of the system designer. To help researchers study thi

Externí odkaz: http://arxiv.org/abs/2311.01011

Zobrazit plný text záznamu

Report

Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Autor: Bailey, Luke, Ong, Euan, Russell, Stuart, Emmons, Scott

Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images that control the behaviour of VLMs at inference time, and introduce the g

Externí odkaz: http://arxiv.org/abs/2309.00236

Zobrazit plný text záznamu

Report

SpeedLimit: Neural Architecture Search for Quantized Transformer Models

Autor: Chai, Yuji, Bailey, Luke, Jin, Yunho, Karle, Matthew, Ko, Glenn G., Brooks, David, Wei, Gu-Yeon, Kung, H. T.

While research in the field of transformer models has primarily focused on enhancing performance metrics such as accuracy and perplexity, practical applications in industry often necessitate a rigorous consideration of inference latency constraints.

Externí odkaz: http://arxiv.org/abs/2209.12127

Zobrazit plný text záznamu