Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Meeus, Matthieu"'
Autor:
Meeus, Matthieu, Shilov, Igor, Jain, Shubham, Faysse, Manuel, Rei, Marek, de Montjoye, Yves-Alexandre
Whether LLMs memorize their training data and what this means, from privacy leakage to detecting copyright violations -- has become a rapidly growing area of research over the last two years. In recent months, more than 10 new methods have been propo
Externí odkaz:
http://arxiv.org/abs/2406.17975
The immense datasets used to develop Large Language Models (LLMs) often include copyright-protected content, typically without the content creator's consent. Copyright traps have been proposed to be injected into the original content, improving conte
Externí odkaz:
http://arxiv.org/abs/2405.15523
Membership Inference Attacks (MIAs) are widely used to evaluate the propensity of a machine learning (ML) model to memorize an individual record and the privacy risk releasing the model poses. MIAs are commonly evaluated similarly to ML models: the M
Externí odkaz:
http://arxiv.org/abs/2405.15423
Questions of fair use of copyright-protected content to train Large Language Models (LLMs) are being actively debated. Document-level inference has been proposed as a new task: inferring from black-box access to the trained model whether a piece of c
Externí odkaz:
http://arxiv.org/abs/2402.09363
With large language models (LLMs) poised to become embedded in our daily lives, questions are starting to be raised about the data they learned from. These questions range from potential bias or misinformation LLMs could retain from their training da
Externí odkaz:
http://arxiv.org/abs/2310.15007
Publikováno v:
ESORICS 2023 workshop Data Privacy Management (DPM) 2023
Synthetic data is emerging as one of the most promising solutions to share individual-level data while safeguarding privacy. While membership inference attacks (MIAs), based on shadow modeling, have become the standard to evaluate the privacy of synt
Externí odkaz:
http://arxiv.org/abs/2307.01701
Publikováno v:
Computer Security ESORICS 2023
Synthetic data is seen as the most promising solution to share individual-level data while preserving privacy. Shadow modeling-based Membership Inference Attacks (MIAs) have become the standard approach to evaluate the privacy risk of synthetic data.
Externí odkaz:
http://arxiv.org/abs/2306.10308
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.