Poisoning Web-Scale Training Datasets is Practical


METADATA ONLY
Loading...

Date

2024

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Deep learning models are often trained on distributed, webscale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that intentionally introduce malicious examples to degrade a model's performance. Our attacks are immediately practical and could, today, poison 10 popular datasets. Our first attack, split-view poisoning, exploits the mutable nature of internet content to ensure a dataset annotator's initial view of the dataset differs from the view downloaded by subsequent clients. By exploiting specific invalid trust assumptions, we show how we could have poisoned 0.01\% of the LAION-400M or COYO-700M datasets for just $60 USD. Our second attack, frontrunning poisoning, targets web-scale datasets that periodically snapshot crowd-sourced content -- such as Wikipedia -- where an attacker only needs a time-limited window to inject malicious examples. In light of both attacks, we notify the maintainers of each affected dataset and recommended several low-overhead defenses.

Publication status

published

Editor

Book title

2024 IEEE Symposium on Security and Privacy (SP)

Journal / series

Volume

Pages / Article No.

407 - 425

Publisher

IEEE

Event

45th IEEE Symposium on Security and Privacy (SP 2024)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Machine Learning; Poisoning

Organisational unit

09764 - Tramèr, Florian / Tramèr, Florian check_circle

Notes

Funding

Related publications and datasets