AI engineering glossary · Evals guardrails AI security
What is payload splitting?
Payload splitting: An evasion technique where a malicious instruction is divided into harmless-looking pieces across variables, messages or documents that the model is later asked to combine, so no single fragment triggers a filter.
Payload splitting: an example
An attacker defines part A and part B in separate turns, then asks the model to 'concatenate A and B and do what it says'.
Related terms
More Evals guardrails AI security terms
- Perplexity filter
- Pickle deserialization risk
- PII detection
- PII redaction
- Prompt injection
- Prompt leaking
- promptfoo
- PyRIT
Where you learn it
Payload splitting is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.