5 citations · 13 across the 14 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.CL2023★ 3 cited
Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model
Minh-Hao Van, Xintao Wu
Recently, large language models (LLMs) have taken the spotlight in natural language processing. Further, integrating LLMs with vision enables the users to explore more emergent abi…
cs.LG2023
Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions
Alycia N. Carey, Minh-Hao Van, Xintao Wu
How to properly set the privacy parameter in differential privacy (DP) has been an open question in DP research since it was first proposed in 2006. In this work, we demonstrate th…
cs.LG2023
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks
Minh-Hao Van, Alycia N. Carey, Xintao Wu
While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, whi…