Zobrazeno 1 - 10
of 2 330
pro vyhledávání: '"Proof of learning"'
Most concurrent blockchain systems rely heavily on the Proof-of-Work (PoW) or Proof-of-Stake (PoS) mechanisms for decentralized consensus and security assurance. However, the substantial energy expenditure stemming from computationally intensive yet
Externí odkaz:
http://arxiv.org/abs/2404.09005
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Ozgur Ural, Kenji Yoshigoe
Publikováno v:
IEEE Access, Vol 12, Pp 169567-169591 (2024)
The rapid advancement of machine learning (ML) technologies necessitates robust security frameworks to protect the integrity of ML model training processes. Proof-of-Learning (PoL) is a critical method for verifying the computational effort in traini
Externí odkaz:
https://doaj.org/article/e31b03075d234cd98812c6566153f07f
Autor:
Fang, Congyu, Jia, Hengrui, Thudi, Anvith, Yaghini, Mohammad, Choquette-Choo, Christopher A., Dullerud, Natalie, Chandrasekaran, Varun, Papernot, Nicolas
Proof-of-Learning (PoL) proposes that a model owner logs training checkpoints to establish a proof of having expended the computation necessary for training. The authors of PoL forego cryptographic approaches and trade rigorous security guarantees fo
Externí odkaz:
http://arxiv.org/abs/2208.03567
Publikováno v:
Aksioma: Jurnal Program Studi Pendidikan Matematika, Vol 11, Iss 4, Pp 2903-2914 (2022)
Abstract Proof-based learning is learning mathematics through proof and proving to strengthen students' concepts. The use of APOS theory (Action, Process, Object, and Schema) aims to describe students' mental structures summarized in Hypothetical Le
Externí odkaz:
https://doaj.org/article/f3bc2786f86449b7b2ef08955e17ec7d
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
In S&P '21, Jia et al. proposed a new concept/mechanism named proof-of-learning (PoL), which allows a prover to demonstrate ownership of a machine learning model by proving integrity of the training procedure. It guarantees that an adversary cannot c
Externí odkaz:
http://arxiv.org/abs/2108.09454
Autor:
Jia, Hengrui, Yaghini, Mohammad, Choquette-Choo, Christopher A., Dullerud, Natalie, Thudi, Anvith, Chandrasekaran, Varun, Papernot, Nicolas
Training machine learning (ML) models typically involves expensive iterative optimization. Once the model's final parameters are released, there is currently no mechanism for the entity which trained the model to prove that these parameters were inde
Externí odkaz:
http://arxiv.org/abs/2103.05633
Conference
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
The progress of deep learning (DL), especially the recent development of automatic design of networks, has brought unprecedented performance gains at heavy computational cost. On the other hand, blockchain systems routinely perform a huge amount of c
Externí odkaz:
http://arxiv.org/abs/2007.15145