DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking

27 July 2022

Papers citing "DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking"

6 / 6 papers shown

Title
ChainMarks: Securing DNN Watermark with Cryptographic ChainACM Asia Conference on Computer and Communications Security (AsiaCCS), 2024 Brian Choi Shu Wang Isabelle Choi Kun Sun 147 0 0 08 May 2025
ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks Zhan Cheng Bo Shen Tianming Sha Yuan Gao Shibo Li Yushun Dong 104 4 0 20 Mar 2025
Watermarking Techniques for Large Language Models: A Survey Yuqing Liang Jiancheng Xiao Wensheng Gan Philip S. Yu OffRL 144 14 0 26 Aug 2024
Wide Flat Minimum Watermarking for Robust Ownership Verification of GANs Jianwei Fei Zhihua Xia B. Tondi Mauro Barni AAML 134 8 0 25 Oct 2023
I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences Daryna Oliynyk Rudolf Mayer Andreas Rauber 180 132 0 16 Jun 2022
Stealing and Evading Malware Classifiers and Antivirus at Low False Positive Conditions M. Rigaki Sebastian Garcia AAML 142 12 0 13 Apr 2022