Search Results for author:
Found 6 papers, 2 papers with code
Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion
With the rise of Machine Learning as a Service (MLaaS) platforms, safeguarding the intellectual property of deep learning models is becoming paramount.
Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
To trace the copyright of deep neural networks, an owner can embed its identity information into its model as a watermark.
R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
We introduce R-Judge, a benchmark crafted to evaluate the proficiency of LLMs in judging and identifying safety risks given agent interaction records.
FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning
In this paper, we propose "FedPrompt" to study prompt tuning in a model split aggregation way using FL, and prove that split aggregation greatly reduces the communication cost, only 0. 01% of the PLMs' parameters, with little decrease on accuracy both on IID and Non-IID data distribution.
Knowledge-Free Black-Box Watermark and Ownership Proof for Image Classification Neural Networks
To confront these challenges, we propose a knowledge-free black-box watermarking scheme for image classification neural networks.
FastCover: An Unsupervised Learning Framework for Multi-Hop Influence Maximization in Social Networks
Finding influential users in social networks is a fundamental problem with many possible useful applications.
