What's New in AVID: AI Vulnerability Database Rebuilt for the Age of AI Agents
AVID releases a major update, with focus on general-purpose AI failures....
· 5 min · Subho Majumdarvulnerabilities
Anyone Can Audit! Users Can Lead Their Own Algorithmic Audits with IndieLabel
ARVA publicly launches IndieLabel, a prototype tool that guides everyday users to perform …...
· 4 min · Michelle S. Lam, Christina A. Pan, Carol Anderson, Nathan Butters, and Borhane Blili-HamelinARVA Announces Support for Open Letter on Voluntary Safe Harbor Protections for Good Faith Testing of Generative AI Systems
Voluntary safe harbor protections are crucial to a thriving AI risk management ecosystem....
· 2 min · Borhane Blili-Hamelin, Carol Anderson, Jekaterina Novikova, Ric McLaughlin, Nathan Butters, Brian Pendleton, and Subho MajumdarAVID Announces Integration with Giskard Scan
Giskard Scan results can now be exported as AVID reports....
· 3 min · Matteo Dora, Subho MajumdarAI Vulnerability Database: 2023 in review
A recap of AVID's work in 2023, and note of gratitude....
· 6 min · Subho Majumdar, Nathan Butters, Borhane Blili-Hamelin, Brian PendletonAVID Announces BiasAware - A Powerful Tool for Detecting Bias in Datasets
A new tool to detect bias in datasets, developed by AVID and hosted on Hugging Face....
· 7 min · Freyam Mehta, Sudipta Ghosh, Carol Anderson, Jekaterina Novikova and Subho MajumdarAVID Announces Integration with garak, a Vulnerability Scanner for LLMs
Vulnerabilities found by garak can now be converted easily into AVID reports....
· 4 min · Leon Derczynski, Carol Anderson, and Subho MajumdarARVA Response to the NTIA AI Accountability Policy Request for Comment
Public Comments from ARVA in Response to NTIA's Request for Comment on AI Accountability Policy...
· 5 min · Carol AndersonLarge Language Models Can Steal Work and Spill Secrets. Here's Why We Should Care.
An overview of the risks to privacy and intellectual property posed by large language models....
· 8 min · Carol Anderson