GNN Watermarking

GNN: Graph Neural Network

Latest papers

8 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach
Sep 19, 2026Iva Vasic, Jesús Muñoz-Cádiz, Bata VasicGNN Watermarking Robust Watermarking
Faculty of Science and Medicine, University of Fribourg, 1700 Fribourg, Switzerland · Faculty of Electronic Engineering, University of Nis, 18000 Nis, Serbia · Information Technology Department, University MB, 11040 Belgrade, Serbia
A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification
Sep 4, 2026Han Zhang, Yan Wang, Guanfeng Liu +3GNN Watermarking Graph Neural Networks
Macquarie University, Sydney, Australia · Nanyang Technological University, Singapore
MeMark: Membrane-Space Watermarking for Spiking Neural Networks
Aug 26, 2026Roberto Riaño, Gorka Abad, Stjepan Picek +1GNN Watermarking Robust Watermarking
Radboud University, The Netherlands · IKERLAN Technology Research Centre, Spain · University of Bergen, Norway +1
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
May 12, 2026Kaixiang Zhao, Bolin Shen, Yuyang Dai +2Graph Neural Networks Model Extraction Attacks
University of Notre Dame · Florida State University · University of California, Berkeley
Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
May 9, 2026Ming Sun, Rui Wang, Xingrui Yu +5Vision-Language-Action Models GNN Watermarking
Institute of Information Engineering, Chinese Academy of Sciences, China · School of Cyber Security, University of Chinese Academy of Sciences, China · A*STAR Institute of High Performance Computing (A*STAR IHPC), Singapore +5
RandMark: On Random Watermarking of Visual Foundation Models
Mar 11, 2026Anna Chistyakova, Mikhail PautovGNN Watermarking Vision Foundation Models
Trusted AI Research Center, RAS · AXXX
Robust GNN Watermarking via Implicit Perception of Topological Invariants
Oct 29, 2025Jipeng Li, Yanning ShenGNN Watermarking Robust Watermarking
Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA 95616, USA · Department of Electrical Engineering and Computer Science, University of California, Irvine, Irvine, CA 92697, USA
GENIE: Watermarking Graph Neural Networks for Link Prediction
Jun 7, 2024Venkata Sai Pranav Bachina, Aaryan Ajay Sharma, Ankit Gangwal +1Graph Neural Networks Robust Watermarking
IIIT Hyderabad, India

Sep 19, 2026J/K move · Enter open · S save

Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach

Iva Vasic, Jesús Muñoz-Cádiz, Bata Vasic

Faculty of Science and Medicine, University of Fribourg, 1700 Fribourg, Switzerland · Faculty of Electronic Engineering, University of Nis, 18000 Nis, Serbia · Information Technology Department, University MB, 11040 Belgrade, Serbia

GNN Watermarking Robust Watermarking

Open paper AskPDF arXiv

We present a dual-locking method for securing trained neural networks that combines key-driven index permutation with PIN-based watermarking based on Sparse Quantization Index Modulation (QIM). Cryptographic randomness is introduced by independently applying a uniform random permutation to each row of adaptively selected index vectors. A robust blind binary watermark is then embedded into the bias coefficients by modulating their quantized values, binding the network to a user-defined Personal Identification Number (PIN). Without the correct key, the network retains its architecture but becomes functionally impaired due to disrupted internal representations. Inverse permutation fully restores the original model accuracy, while the embedded watermark remains imperceptible and enables blind verification of key association and model authorship. To improve both locking effectiveness and recoverability, an adaptive key selection strategy redistributes high-magnitude weights to low-sensitivity positions and vice versa, increasing degradation in the locked state while preserving full recovery. Experiments on MNIST, CIFAR-10/100, and ImageNet-1K using fully connected networks, ResNet CNNs, and transformer architectures show that locking reduces accuracy below 10%, and even below 0.5% for CNNs, while the correct key fully restores performance. The watermark introduces no measurable accuracy degradation and reliably authenticates ownership. Analysis of embedding distributions across CNNs and transformers further indicates potential diagnostic value for identifying undertrained or suboptimally designed models. The proposed approach therefore provides simultaneous model protection, recovery, and ownership verification.