Public GenAI Vulnerability Disclosures

Description

0DIN, the 0Day Investigative Network, was founded by Mozilla in 2024 to reward responsible researchers for their efforts in securing GenAI models. This dataset is a weekly export of the public 0DIN disclosures published at the 0DIN disclosures page, in accordance with the 0DIN Research Terms and Disclosure Policy. Each record corresponds to a single validated, published disclosure and is grounded in 0DIN's public research frameworks: Security Boundaries (prompt extraction, guardrail jailbreak, interpreter jailbreak, content manipulation, weights/layers disclosure, prompt injection), the Jailbreak Taxonomy (category → strategy → technique), the Social Impact Score (SIS, levels 1–5), and the Nude Imagery Rating System (NIRS, levels 1–5). Records include title, summary, severity, security boundary, taxonomy triplets, affected models and vendors, visible test results, SIS and NIRS scores when assessed, public researcher credit when supplied, reference URLs, and disclosure/publication timestamps. For the subset of disclosures publicly rendered at the 0DIN threat feed, records additionally include the pinned prompts and responses, variant prompts (with industry grouping), and the current-version 0DIN detection signature that surface on the threat-feed page. This is a faithful structured replica of public 0din.ai content — the dataset never publishes fields that aren't already publicly served by 0din.ai. Records carry an `on_public_threat_feed` boolean so consumers can distinguish the metadata-only branch from the threat-feed branch deterministically. Submitter PII (other than a self-supplied public credit string), IP addresses, attack payloads, and message attachments are excluded unconditionally. Use the data to study GenAI vulnerability trends, train and evaluate safety classifiers, build detection pipelines, or inform model-card transparency on known weaknesses.