Deep intellectual property protection: A survey

Y Sun, T Liu, P Hu, Q Liao, S Fu, N Yu, D Guo… - arXiv preprint arXiv …, 2023 - arxiv.org
Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made
revolutionary progress in recent years, and are widely used in various fields. The high …

SoK: Unintended Interactions among Machine Learning Defenses and Risks

V Duddu, S Szyller, N Asokan - arXiv preprint arXiv:2312.04542, 2023 - arxiv.org
Machine learning (ML) models cannot neglect risks to security, privacy, and fairness.
Several defenses have been proposed to mitigate such risks. When a defense is effective in …

Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process

V Pozdnyakov, A Kovalenko, I Makarov… - IEEE Open Journal …, 2024 - ieeexplore.ieee.org
Integrating machine learning into Automated Control Systems (ACS) enhances decision-
making in industrial process management. One of the limitations to the widespread adoption …

Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion

H Zhu, S Liang, W Hu, F Li, J Jia, S Wang - arXiv preprint arXiv …, 2024 - arxiv.org
With the rise of Machine Learning as a Service (MLaaS) platforms, safeguarding the
intellectual property of deep learning models is becoming paramount. Among various …

Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience

J Thakkar, G Zizzo, S Maffeis - arXiv preprint arXiv:2312.14260, 2023 - arxiv.org
Machine learning models are being used in an increasing number of critical applications;
thus, securing their integrity and ownership is critical. Recent studies observed that …

Ownership and Confidentiality in Machine Learning

S Szyller - 2023 - aaltodoc.aalto.fi
Statistical and machine learning (ML) models have been the primary tools for data-driven
analysis for decades. Recent theoretical progress in deep neural networks (DNNs) coupled …

Deep Watermarking for Deep Intellectual Property Protection: A Comprehensive Survey

Y Sun, L Liu, N Yu, Y Liu, Q Tian, D Guo - Available at SSRN 4697020 - papers.ssrn.com
Highlights We provide a comprehensive survey of deep learning watermarking. We present
the problem definition, criteria, challenges, and threats of watermarking. We give a …