51 citations · 68 across the 8 of their papers we have counts for
8 papers
On the independence problem of Newton's first law
Ido Yavetz, Ehud Aharoni
Newton's laws of motion pose an apparent problem, sometimes referred to as "the independence problem": the first law seems to be a simple consequence of the second law, raising the…
Power-Softmax: Towards Secure LLM Inference over Encrypted Data
Itamar Zimerman, Allon Adir, Ehud Aharoni +7
Modern cryptographic methods for implementing privacy-preserving LLMs such as \gls{HE} require the LLMs to have a polynomial form. Forming such a representation is challenging beca…
Generating One-Hot Maps under Encryption
Ehud Aharoni, Nir Drucker, Eyal Kushnir +2
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 Encrypt…
Efficient Pruning for Machine Learning Under Homomorphic Encryption
Ehud Aharoni, Moran Baruch, Pradip Bose +8
Privacy-preserving machine learning (PPML) solutions are gaining widespread popularity. Among these, many rely on homomorphic encryption (HE) that offers confidentiality of the mod…
Privacy-preserving record linkage using local sensitive hash and private set intersection
Allon Adir, Ehud Aharoni, Nir Drucker +4
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, whil…
HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
Ehud Aharoni, Allon Adir, Moran Baruch +9
Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage…
Optimal and Maximin Procedures for Multiple Testing Problems
Saharon Rosset, Ruth Heller, Amichai Painsky +1
Multiple testing problems are a staple of modern statistical analysis. The fundamental objective of multiple testing procedures is to reject as many false null hypotheses as possib…
Generalized Alpha Investing: Definitions, Optimality Results, and Application to Public Databases
Ehud Aharoni, Saharon Rosset
The increasing prevalence and utility of large, public databases necessitates the development of appropriate methods for controlling false discovery. Motivated by this challenge, w…