From 43d1aa511b22d05c79a58769848342067e944641 Mon Sep 17 00:00:00 2001 From: Sefik Ilkin Serengil Date: Tue, 4 Mar 2025 09:45:59 +0000 Subject: [PATCH] Update README.md why encrypt? --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 98944d0..e8830ab 100644 --- a/README.md +++ b/README.md @@ -401,7 +401,7 @@ Conversely, if your task involves facial recognition on small to moderate-sized **Encrypt Embeddings** - `Demo with PHE`, [`Demo with FHE`](https://youtu.be/njjw0PEhH00) -Even though vector embeddings are not reversible to original images, they still contain sensitive information such as fingerprints, making their security critical. Traditional encryption methods like AES are very safe but limited in securely utilizing cloud computational power for distance calculations. Herein, [homomorphic Encryption](https://youtu.be/3ejI0zNPMEQ), allowing calculations on encrypted data, offers a robust alternative. In summary, we are able to compute similarity between encrypted embeddings with homomorphic encryption. +Even though vector embeddings are not reversible to original images, they still contain sensitive information such as fingerprints, making their security critical. Encrypting embeddings is essential for higher security applications to prevent adversarial attacks that could manipulate or extract sensitive information. Traditional encryption methods like AES are very safe but limited in securely utilizing cloud computational power for distance calculations. Herein, [homomorphic Encryption](https://youtu.be/3ejI0zNPMEQ), allowing calculations on encrypted data, offers a robust alternative. In summary, we are able to compute similarity between encrypted embeddings with homomorphic encryption. ```python from lightphe import LightPHE