2.1 · Preprocessing integrity

Explore 1 source-supported AI security cases for 2.1 · Preprocessing integrity in Databricks DASF 3.0, with evidence, scope, and defensive analysis.

Risk category

Errors or malicious changes are introduced while data is prepared for a model. Affected operations can include numerical transformations, aggregation, text or image encoding, feature creation, joins, missing-value handling, and formatting. Insiders or external attackers can compromise either the preprocessing work itself or the repository supplying its data, changing what the model ultimately receives.

Official framework source ↗ · Open interactive explorer ↗

Validated Research · · Practical overlap

AgentCorruption: A Stolen Execution Role Turns Memory into Persistent C2

Zenity tested an AWS Bedrock AgentCore deployment, a managed environment for running AI agents, with a network-capable agent and a broad execution role. The agent relayed temporary role credentials from its metadata endpoint. Off-platform API calls then reached other memories and agents. The distinctive persistence path wrote short-term conversation events that configured extraction strategies could turn into long-term records; later retrieval directed the agent to a mutable command page. The reach was demonstrated within an account and region, not as a microVM escape or automatic cross-account compromise. The researchers observed major default-role restrictions on September 29; existing deployed roles still require independent inspection.

Why it relates: The extraction process can transform attacker-authored conversation text into longer-lived model context. The common boundary is data transformation integrity; no numerical feature engineering or training preprocessing is claimed.

Controlled broad-role AgentCore deployment with separate direct API and retained-memory/C2 branches; account/region scope, tool prerequisites and later default-role restrictions remain explicit.

AIA · Read the full case ↗ · SecureFlow · Read the full case ↗