3.2 · Ineffective storage and encryption

Explore 1 source-supported AI security cases for 3.2 · Ineffective storage and encryption in Databricks DASF 3.0, with evidence, scope, and defensive analysis.

Risk category

Training datasets are stored or managed without adequate protection against unauthorized access and modification. The organization needs to understand who can reach the data sources and what happens if an attacker gains control of them. Public sources are particularly important because local access controls do not prevent an attacker from changing data at its external origin.

Official framework source ↗ · Open interactive explorer ↗

Validated Research ·

Web-Scale Data Poisoning: Split-View Attack

Many recent large-scale datasets are distributed as a list of URLs pointing to individual datapoints. The researchers show that many of these datasets are vulnerable to a "split-view" poisoning attack. The attack exploits the fact that the data viewed when it was initially collected may differ from the data viewed by a user during training. The researchers identify expired and buyable domains that once hosted dataset content, making it possible to replace portions of the dataset with poisoned data. They demonstrate that for 10 popular web-scale datasets, enough of the domains are purchasable to successfully carry out a poisoning attack.

Why it relates: Published dataset URL lists identify exactly which external image origins will be downloaded. Buying expired listed domains can replace those examples, crossing the original curator-to-later-downloader integrity boundary. Public downloads were not poisoned in the study; downstream model effects were tested by local image replacement and CLIP retraining.

Many recent large-scale datasets are distributed as a list of URLs pointing to individual datapoints. The researchers show that many of these datasets are vulnerable to a "split-view" poisoning attack. The attack exploits the fact that the data viewed when it was initially collected may differ from the data viewed by a user during training. The researchers identify expired and buyable domains that once hosted dataset content, making it possible to replace portions of the dataset with poisoned data. They demonstrate that for 10 popular web-scale datasets, enough of the domains are purchasable to successfully carry out a poisoning attack.

SecureFlow · Read the full case ↗