ASIDE: Architectural Separation of Instructions and Data in Language Models

Understand

Despite their remarkable performance, large language models lack elementary safety features, making them susceptible to numerous malicious attacks.

• In particular, previous work has identified the absence of an intrinsic separation between instructions and data as the root cause of the success of prompt injection attacks.
• In this work, we propose a new architectural element, ASIDE, that allows language models to clearly separate instructions and data at the level of token embeddings.
• ASIDE applies an orthogonal rotation to the embeddings of data tokens, thus creating clearly distinct representations of instructions and data tokens without introducing any additional parameters.