3 papers
cs.LG2026
MANCE: Manifold Aware Concept Erasure
Matan Avitan, Yoav Goldberg, Yanai Elazar
Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many co…
cs.LG2025
Efficient Decoding Methods for Language Models on Encrypted Data
Matan Avitan, Moran Baruch, Nir Drucker +2
Large language models (LLMs) power modern AI applications, but processing sensitive data on untrusted servers raises privacy concerns. Homomorphic encryption (HE) enables computati…
cs.LG2024
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…