# Lethean Attack: An Online Data Poisoning Technique

arXiv: https://arxiv.org/abs/2011.12355 · HTML: https://mlsanity.com/paper/2011.12355/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 1 of 1)

- [Transfer-based Adversarial Poisoning Attacks for Online (MIMO-)Deep Receviers](https://mlsanity.com/paper/2409.02430/) (2024)

## Abstract (arXiv)

Data poisoning is an adversarial scenario where an attacker feeds a specially crafted sequence of samples to an online model in order to subvert learning. We introduce Lethean Attack, a novel data poisoning technique that induces catastrophic forgetting on an online model. We apply the attack in the context of Test-Time Training, a modern online learning framework aimed for generalization under distribution shifts. We present the theoretical rationale and empirically compare it against other sample sequences that naturally induce forgetting. Our results demonstrate that using lethean attacks, an adversary could revert a test-time training model back to coin-flip accuracy performance using a short sample sequence.