SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.10445 · 2023

Memorization for Good: Encryption with Autoregressive Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Over-parameterized neural language models (LMs) can memorize and recite long sequences of training data. While such memorization is normally associated with undesired properties such as overfitting and information leaking, our work casts memorization as an unexplored capability of LMs. We propose the first symmetric encryption algorithm with autoregressive language models (SELM). We show that autoregressive LMs can encode arbitrary data into a compact real-valued vector (i.e., encryption) and then losslessly decode the vector to the original message (i.e., decryption) via random subspace optimization and greedy decoding. While SELM is not amenable to conventional cryptanalysis, we investigate its security through a novel empirical variant of the classic IND-CPA (indistinguishability under chosen-plaintext attack) game and show promising results on security. Our code and datasets are available at https://github.com/OSU-NLP-Group/SELM.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.10445")
get_code_for_paper("2305.10445")
have("2305.10445")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.10445.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.10445.svg)](https://syntology.ai/paper/2305.10445)

Connect an agent — have() is free.