Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Drucker, Nir"'
Autor:
Zimerman, Itamar, Adir, Allon, Aharoni, Ehud, Avitan, Matan, Baruch, Moran, Drucker, Nir, Lerner, Jenny, Masalha, Ramy, Meiri, Reut, Soceanu, Omri
Modern cryptographic methods for implementing privacy-preserving LLMs such as Homomorphic Encryption (HE) require the LLMs to have a polynomial form. Forming such a representation is challenging because Transformers include non-polynomial components,
Externí odkaz:
http://arxiv.org/abs/2410.09457
Designing privacy-preserving deep learning models is a major challenge within the deep learning community. Homomorphic Encryption (HE) has emerged as one of the most promising approaches in this realm, enabling the decoupling of knowledge between the
Externí odkaz:
http://arxiv.org/abs/2311.08610
Autor:
Kadhe, Swanand Ravindra, Ludwig, Heiko, Baracaldo, Nathalie, King, Alan, Zhou, Yi, Houck, Keith, Rawat, Ambrish, Purcell, Mark, Holohan, Naoise, Takeuchi, Mikio, Kawahara, Ryo, Drucker, Nir, Shaul, Hayim, Kushnir, Eyal, Soceanu, Omri
The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment network system (PNS) and its partner banks. Trust among these financial institutions is limited
Externí odkaz:
http://arxiv.org/abs/2310.19304
One-hot maps are commonly used in the AI domain. Unsurprisingly, they can also bring great benefits to ML-based algorithms such as decision trees that run under Homomorphic Encryption (HE), specifically CKKS. Prior studies in this domain used these m
Externí odkaz:
http://arxiv.org/abs/2306.06739
Autor:
Drucker, Nir, Zimerman, Itamar
Homomorphic Encryption (HE) is a cryptographic tool that allows performing computation under encryption, which is used by many privacy-preserving machine learning solutions, for example, to perform secure classification. Modern deep learning applicat
Externí odkaz:
http://arxiv.org/abs/2306.06736
Autor:
Baruch, Moran, Drucker, Nir, Ezov, Gilad, Goldberg, Yoav, Kushnir, Eyal, Lerner, Jenny, Soceanu, Omri, Zimerman, Itamar
Training large-scale CNNs that during inference can be run under Homomorphic Encryption (HE) is challenging due to the need to use only polynomial operations. This limits HE-based solutions adoption. We address this challenge and pioneer in providing
Externí odkaz:
http://arxiv.org/abs/2304.14836
Autor:
Aharoni, Ehud, Baruch, Moran, Bose, Pradip, Buyuktosunoglu, Alper, Drucker, Nir, Pal, Subhankar, Pelleg, Tomer, Sarpatwar, Kanthi, Shaul, Hayim, Soceanu, Omri, Vaculin, Roman
Privacy-preserving neural network (NN) inference solutions have recently gained significant traction with several solutions that provide different latency-bandwidth trade-offs. Of these, many rely on homomorphic encryption (HE), a method of performin
Externí odkaz:
http://arxiv.org/abs/2207.03384
Autor:
Adir, Allon, Aharoni, Ehud, Drucker, Nir, Kushnir, Eyal, Masalha, Ramy, Mirkin, Michael, Soceanu, Omri
The amount of data stored in data repositories increases every year. This makes it challenging to link records between different datasets across companies and even internally, while adhering to privacy regulations. Address or name changes, and even d
Externí odkaz:
http://arxiv.org/abs/2203.14284
Privacy-preserving deep neural network (DNN) inference is a necessity in different regulated industries such as healthcare, finance and retail. Recently, homomorphic encryption (HE) has been used as a method to enable analytics while addressing priva
Externí odkaz:
http://arxiv.org/abs/2111.03362
Autor:
Aharoni, Ehud, Adir, Allon, Baruch, Moran, Drucker, Nir, Ezov, Gilad, Farkash, Ariel, Greenberg, Lev, Masalha, Ramy, Moshkowich, Guy, Murik, Dov, Shaul, Hayim, Soceanu, Omri
Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic Encryption (HE),
Externí odkaz:
http://arxiv.org/abs/2011.01805