Glossary · Term

gradient-free attack

← all terms

Definition

Plain language

Tampering with a model without retraining it, using only simple arithmetic on its internal numbers.

As stated in the literature

Weight or activation manipulation that requires no backpropagation or training data, e.g. difference-of-means direction estimation followed by projection removal; typically cheap, capability-preserving, and effective against published tamper-resistance schemes.

Also called: gradient-free attacks, gradient-free

Why it matters: Because it needs no training run and preserves the model's abilities, it puts tampering within reach of people with modest hardware and no research budget.

For example, an attacker averages the model's internal numbers on two sets of prompts, subtracts one from the other, and edits the result out of the weights — no training data required.

Heard on the show

“That's a monitoring-and-control story for agents that take real actions — legible, gradient-free, inference-time.”
Episode 175 — One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent

Mentioned in 1 episode

  1. 175
    One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent

Related terms