9 citations · 14 across the 3 of their papers we have counts for
3 papers
cs.CL2023★ 5 cited
Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information
Zhengmian Hu, Gang Wu, Saayan Mitra +4
In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attac…
cs.CV2021★ 9 cited
VPN: Video Provenance Network for Robust Content Attribution
Alexander Black, Tu Bui, Simon Jenni +2
We present VPN - a content attribution method for recovering provenance information from videos shared online. Platforms, and users, often transform video into different quality, c…
cs.CV2021
OSCAR-Net: Object-centric Scene Graph Attention for Image Attribution
Eric Nguyen, Tu Bui, Vishy Swaminathan +1
Images tell powerful stories but cannot always be trusted. Matching images back to trusted sources (attribution) enables users to make a more informed judgment of the images they e…