Supplemental readings for Securing AI Data Sets - #65
Open
zbraiterman wants to merge 18 commits into
Open
Conversation
Added sections for securing data sets and useful books related to security topics in AI.
Added guidelines for securing datasets used by AI models, including verifying provenance, integrity, and encryption. Provided references to relevant resources for further guidance.
Added a section on securing datasets used by AI models, emphasizing their importance and the risks of compromised data.
Added guidelines for securing datasets in AI development, including verification, encryption, and access auditing.
Added links to external tools for better reference.
Added a link to the definition of Personally Identifiable Information (PII) masking for clarity.
Expanded guidelines on verifying training data provenance, including maintaining metadata and restrictions on dataset sources.
Added details on verifying dataset integrity and actions for developers.
Added detailed guidelines for encrypting data at rest and in transit, including encryption algorithms, key management, and compliance measures.
Added guidelines for identifying and handling sensitive information in datasets, including PII, PHI, and other confidential data.
Added guidelines for minimizing data collection, processing, and retention in AI applications.
Added recommendations for integrating dataset version control tools and managing large files with Git-LFS.
Added detailed guidelines for verifying and securing third-party datasets before integration into AI workflows.
Added detailed guidelines for auditing dataset access and securely managing dataset retention and deletion.
Added section on input validation for AI models, including resources for LLM input sanitization and traditional security guidance.
Corrected the formatting of a link and improved clarity in the text regarding OWASP standards.
Added section on prompt injection and related resources.
Added a section on Output Data Control, highlighting its importance in AI security and referencing OWASP LLM Top 10.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I took a first pass at the supplemental readings for the "Securing Data Sets" section of Module 15 ("Security of and for AI)".