Data Vault

Summary: Privacy in the Age of Generative AI

1. LLMs have no DELETE button. There is no straightforward mechanism to “unlearn” specific information, no equivalent to deleting a row in your database user table. In a world where “right to be forgotten” is central to many privacy regulations, using LLMs presents some difficult challenges.
2. Data Privacy Vault is IEEE’s recommended architecture for securely storing, managing and utilizing sensitive customer’s Personally Identifiable Information (PII).
3. Data of a sensitive nature can seep into LLM during training as well as inference. During training, information of a sensitive na ture may be ingested from documents that are not anonymized or redacted for sensitive information. During inference, a prompt may inadvertently provide sensitive information. For example, a prompt that requests the LLM to summarize a will with sensitive information.
4. Only way to delete information from an LLM is to train it from scratch! Hence, don’t let sensitive information get in in the first place.
5. Key consideration for anonymization is Referential Integrity.
   

   Synthetic Data

   ⇄

   Original Sensitive Information

6. Is private LLM a solution? As opposed to managed service like OpenAI’s ChatGPT. Who will update the base model to keep up with new releases? Expensive!
7. Base model v. Fine-tuning (Andrej Karpathy’s Intro to Large Language Models)

   

8. Private LLM does not address privacy concerns!
9. Privacy: WHO sees WHAT

   

10. Data Privacy Vault – Principle:
    

    

11. Tokenization: Swap sensitive data for tokens. A token is a reference for some sensitive data somewhere else. Thus, reference something while providing obfuscation.

    

    Fig. shows sensitive data being replaced by tokens by the application frontend through the Data Privacy Vault. The assets downstream of the app – app database, warehouse, reports and/or analytics – then only “know” the tokenized data. These are not tokens in the sense of tokenization in LLMs but tokens that hold a reference to the original data which is stored in the Data Privacy Vault.Vault not only stores and generates de-identified data, it tightly controls access to sensitive data through a zero-trust model, where user accounts are managed through explicit access control policies. 777-123-4567 → ABC4567

12. Fig. shows sensitive data under explicit access control to address WHO sees WHAT. 

    

    Using privacy enhancing techniques such as polymorphic encryption and tokenization, sensitive data can be de-identified in a way that preserves referential integrity. 

13. Prompt Seepage: Sensitive data may also enter a model during inference. For example, a prompt is created asking for a summary of a will. The vault detects the sensitive information, de-identifies it, and shares a non-sensitive version of the prompt with the LLM. Since the LLM was trained on non-sensitive and de-identified data, inference can be carried out as normal.