Protecting artificial intelligence IPs: a survey of watermarking and fingerprinting for machine learning. Regazzoni, F., Palmieri, P., Smailbegovic, F., Cammarota, R., & Polian, I. CAAI Transactions on Intelligence Technology, 6(2):180–191, 2021. _eprint: https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/cit2.12029
Protecting artificial intelligence IPs: a survey of watermarking and fingerprinting for machine learning [link]Paper  doi  abstract   bibtex   
Artificial intelligence (AI) algorithms achieve outstanding results in many application domains such as computer vision and natural language processing. The performance of AI models is the outcome of complex and costly model architecture design and training processes. Hence, it is paramount for model owners to protect their AI models from piracy – model cloning, illegitimate distribution and use. IP protection mechanisms have been applied to AI models, and in particular to deep neural networks, to verify the model ownership. State-of-the-art AI model ownership protection techniques have been surveyed. The pros and cons of AI model ownership protection have been reported. The majority of previous works are focused on watermarking, while more advanced methods such fingerprinting and attestation are promising but not yet explored in depth. This study has been concluded by discussing possible research directions in the area.
@article{regazzoniProtectingArtificialIntelligence2021,
	title = {Protecting artificial intelligence {IPs}: a survey of watermarking and fingerprinting for machine learning},
	volume = {6},
	copyright = {© 2021 The Authors. CAAI Transactions on Intelligence Technology published by John Wiley \& Sons Ltd on behalf of The Institution of Engineering and Technology and Chongqing University of Technology.},
	issn = {2468-2322},
	shorttitle = {Protecting artificial intelligence {IPs}},
	url = {https://onlinelibrary.wiley.com/doi/abs/10.1049/cit2.12029},
	doi = {10.1049/cit2.12029},
	abstract = {Artificial intelligence (AI) algorithms achieve outstanding results in many application domains such as computer vision and natural language processing. The performance of AI models is the outcome of complex and costly model architecture design and training processes. Hence, it is paramount for model owners to protect their AI models from piracy – model cloning, illegitimate distribution and use. IP protection mechanisms have been applied to AI models, and in particular to deep neural networks, to verify the model ownership. State-of-the-art AI model ownership protection techniques have been surveyed. The pros and cons of AI model ownership protection have been reported. The majority of previous works are focused on watermarking, while more advanced methods such fingerprinting and attestation are promising but not yet explored in depth. This study has been concluded by discussing possible research directions in the area.},
	language = {en},
	number = {2},
	urldate = {2025-12-16},
	journal = {CAAI Transactions on Intelligence Technology},
	author = {Regazzoni, Francesco and Palmieri, Paolo and Smailbegovic, Fethulah and Cammarota, Rosario and Polian, Ilia},
	year = {2021},
	note = {\_eprint: https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/cit2.12029},
	keywords = {data protection, deep learning (artificial intelligence), fingerprint identification, industrial property, watermarking},
	pages = {180--191},
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021