research
∙
06/30/2023
Provable Robust Watermarking for AI-Generated Text
As AI-generated text increasingly resembles human-written content, the a...
share
research
∙
06/12/2023
"Private Prediction Strikes Back!” Private Kernelized Nearest Neighbors with Individual Renyi Filter
Most existing approaches of differentially private (DP) machine learning...
research
∙
06/02/2023
Generative Autoencoders as Watermark Attackers: Analyses of Vulnerabilities and Threats
Invisible watermarks safeguard images' copyrights by embedding hidden me...
research
∙
02/06/2023
Protecting Language Generation Models via Invisible Watermarking
Language generation models have been an increasingly powerful enabler fo...
research
∙
12/14/2022
Pre-trained Language Models can be Fully Zero-Shot Learners
How can we extend a pre-trained model to many language understanding tas...
research
∙
10/07/2022
Distillation-Resistant Watermarking for Model Protection in NLP
How can we protect the intellectual property of trained NLP models? Mode...
research
∙
05/04/2022
Provably Confidential Language Modelling
Large language models are shown to memorize privacy information such as ...
research
∙
03/15/2022
Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation
How to learn highly compact yet effective sentence representation? Pre-t...
research
∙
01/23/2021
An Optimal Reduction of TV-Denoising to Adaptive Online Learning
We consider the problem of estimating a function from n noisy samples wh...
research
∙
07/19/2020
A Multi-Semantic Metapath Model for Large Scale Heterogeneous Network Representation Learning
Network Embedding has been widely studied to model and manage data in a ...
research
∙
10/01/2019