A survey on security analysis of machine learning-oriented hardware and software intellectual property

Tauhid, Ashraful; Xu, Lei; Rahman, Mostafizur; Tomai, Emmett

doi:10.1016/j.hcc.2023.100114

Cited by 10 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new study by Tauhid et al (2023) tackles a critical issue: protecting intellectual property (IP) in the world of hardware and software. Here's what they explore: (1) The current state of intellectual property rights and the latest developments in IP protection research.…”

Section: Literature Reviewmentioning

confidence: 99%

Patent Analysis in the Realm of Machine Learning in Manufacturing

Akkalender,

Yalçın

2024

Sosyal Bilimler Metinleri

View full text Add to dashboard Cite

Patent analysis reveals a surge in machine learning for manufacturing since 1980, hinting at its potential beyond traditional applications. This study explores this trend through three key questions: how machine learning use is evolving, what technological areas patents cover, and where these machine learning applications are being developed. The analysis finds machine learning impacting areas like medical devices and quality control across various industries. These findings suggest that machine learning can improve efficiency, ensure quality, and drive innovation, paving the way for future research into specific applications, productivity impacts, and potential challenges. Patent data from Lens.org was visualized employing of BibExcel, Pajek and VOSviewer.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Patent Analysis in the Realm of Machine Learning in Manufacturing

Akkalender,

Yalçın

2024

Sosyal Bilimler Metinleri

View full text Add to dashboard Cite

show abstract

“…Recent years have witnessed a surge in interest regarding intellectual property (IP) protection for ML models, with attention spanning both academia and industry (Xue, Wang, and Liu 2021;Chen et al 2018;Tauhid et al 2023). The central theme of current approaches revolves around embedding distinctive information within the ML model or its training data.…”

Section: Introductionmentioning

confidence: 99%

EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection

Mu,

Wang,

Huang

et al. 2024

AAAI

View full text Add to dashboard Cite

In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important. Within this context, machine learning (ML) models, being highly valuable digital assets, have gained significant attention for IP protection. This paper introduces a practical encryption-based framework called EncryIP, which seamlessly integrates a public-key encryption scheme into the model learning process. This approach enables the protected model to generate randomized and confused labels, ensuring that only individuals with accurate secret keys, signifying authorized users, can decrypt and reveal authentic labels. Importantly, the proposed framework not only facilitates the protected model to multiple authorized users without requiring repetitive training of the original ML model with IP protection methods but also maintains the model's performance without compromising its accuracy. Compared to existing methods like watermark-based, trigger-based, and passport-based approaches, EncryIP demonstrates superior effectiveness in both training protected models and efficiently detecting the unauthorized spread of ML models.

show abstract