factual

Adversarial attacks are the cipher avalanche property

Adversarial attacks on image classifiers—finding a tiny input perturbation that completely changes the output classification—are exactly the avalanche property that ciphers are designed to have; it is the desired case in cryptography but the undesired failure case in neural networks.

factualpending

Speaker

Reiner Pope

Evidence Quote

“Adversarial attacks on image classification models are about finding a very small perturbation of the image that totally changes the classification, totally changes the output. That is the common case in ciphers, whereas that’s the undesired case in neural nets.”

Source

Dwarkesh Patel Podcast - Reiner Pope – The math behind how LLMs are trained and served— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:34:09 AM

Your notes

Loading notes...