000 04070naa a22005417i 4500
001 UMUN-OA-20261005-CYB-009
003 local
005 20261005174814.0
006 m o d
007 cr||||||||||||
008 261005s2024 xx o u000 0 eng d
024 7 _a10.3390/info15110697
_2doi
035 _a(local)OpenAlex:W4404024323
040 _alocal
_beng
_clocal
041 0 _aeng
100 0 _aGeorgios Feretzakis
_eauthor.
245 1 0 _aPrivacy-Preserving Techniques in Generative AI and Large Language Models: A Narrative Review /
_cGeorgios Feretzakis; Konstantinos Papaspyridis; Aris Gkoulalas-Divanis [and others].
264 1 _a[Place of publication not identified] :
_bMultidisciplinary Digital Publishing Institute,
_c2024.
300 _a1 online resource (1 article).
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
500 _aPublication type: Review article.
500 _aLinked open-access copy: published version.
506 0 _aOpen access; no subscription required for the linked open-access version.
_fUnrestricted online access
_2star
520 3 _aGenerative AI, including large language models (LLMs), has transformed the paradigm of data generation and creative content, but this progress raises critical privacy concerns, especially when models are trained on sensitive data. This review provides a comprehensive overview of privacy-preserving techniques aimed at safeguarding data privacy in generative AI, such as differential privacy (DP), federated learning (FL), homomorphic encryption (HE), and secure multi-party computation (SMPC). These techniques mitigate risks like model inversion, data leakage, and membership inference attacks, which are particularly relevant to LLMs. Additionally, the review explores emerging solutions, including privacy-enhancing technologies and post-quantum cryptography, as future directions for enhancing privacy in generative AI systems. Recognizing that achieving absolute privacy is mathematically impossible, the review emphasizes the necessity of aligning technical safeguards with legal and regulatory frameworks to ensure compliance with data protection laws. By discussing the ethical and legal implications of privacy risks in generative AI, the review underscores the need for a balanced approach that considers performance, scalability, and privacy preservation. The findings highlight the need for ongoing research and innovation to develop privacy-preserving techniques that keep pace with the scaling of generative AI, especially in large language models, while adhering to regulatory and ethical standards.
540 _aCreative Commons Attribution (licence family recorded by the source; version not supplied in metadata).
_uhttps://openalex.org/W4404024323
546 _aIn English.
588 0 _aDescription generated from OpenAlex bibliographic metadata retrieved on 5 October 2026; full text linked from the source.
590 _aCourse allocation: B. Sc. Cyber Security.
650 4 _aprivacy-preserving techniques
650 4 _alarge language models
650 4 _agenerative AI
650 4 _adifferential privacy
650 4 _afederated learning
650 4 _ahomomorphic encryption
653 _aB. Sc. Cyber Security
653 _aUMUN open access collection
653 _aprivacy preserving
655 4 _aReview articles.
700 0 _aKonstantinos Papaspyridis
_eauthor.
700 0 _aAris Gkoulalas-Divanis
_eauthor.
700 0 _aVassilios S. Verykios
_eauthor.
773 0 _tInformation
_gVol. 15, no. 11, (2024), pages/article 697
_x2078-2489
856 4 0 _uhttps://utoronto.scholaris.ca/bitstreams/72b525ae-3d0e-4baf-a988-e42c29a203a8/download
_yRead open-access publication
_zOpen access. Access and licence reported by the source; this host could not be independently checked by automation.
_70
884 _aCourse selection and automated MARC21 enrichment from OpenAlex metadata.
_g20261005
_khttps://openalex.org/W4404024323
_qlocal
942 _n0
999 _c436
_d436