all AI news
DeepEclipse: How to Break White-Box DNN-Watermarking Schemes
March 7, 2024, 5:42 a.m. | Alessandro Pegoraro, Carlotta Segna, Kavita Kumari, Ahmad-Reza Sadeghi
cs.LG updates on arXiv.org arxiv.org
Abstract: Deep Learning (DL) models have become crucial in digital transformation, thus raising concerns about their intellectual property rights. Different watermarking techniques have been developed to protect Deep Neural Networks (DNNs) from IP infringement, creating a competitive field for DNN watermarking and removal methods. The predominant watermarking schemes use white-box techniques, which involve modifying weights by adding a unique signature to specific DNN layers. On the other hand, existing attacks on white-box watermarking usually require knowledge …
abstract arxiv become box concerns cs.cr cs.lg deep learning digital digital transformation dnn infringement intellectual property networks neural networks property protect rights transformation type watermarking
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
#13721 - Data Engineer - AI Model Testing
@ Qualitest | Miami, Florida, United States
Elasticsearch Administrator
@ ManTech | 201BF - Customer Site, Chantilly, VA