More sources that could be integrated:
Securing AI: How Traditional Vulnerability Disclosure Must Adapt (CSET: Lohn and Hoffman 2022)
Joint Recommendation for Language Model Deployment (Cohere, OpenAI, and AI21 Labs 2022)
Includes the principles “Document known weaknesses and vulnerabilities” and “Publicly disclose lessons learned regarding LLM safety and misuse”
https://arxiv.org/abs/2308.14752
https://twitter.com/GretchenMarina/status/1696702861952926179
“Reporting Information on AI Risk Factors and Incidents” in “Actionable Guidance for High-Consequence AI Risk Management” (Barrett et al. 2022, revised 2023)
NIST AI RMF: GOVERN §4.3, MEASURE §3.3, and MANAGE §4.3 (NIST 2023)
CSET AI Harm Taxonomy for AIID and Annotation Guide (CSET 2023)
Confidence-Building Measures for Artificial Intelligence (Shoker et al. 2023)
Suggests sharing incidents or making incident-sharing agreements could be good as a CBM
Guide to Cyber Threat Information Sharing (NIST 2016)
More sources that could be integrated:
Securing AI: How Traditional Vulnerability Disclosure Must Adapt (CSET: Lohn and Hoffman 2022)
Joint Recommendation for Language Model Deployment (Cohere, OpenAI, and AI21 Labs 2022)
Includes the principles “Document known weaknesses and vulnerabilities” and “Publicly disclose lessons learned regarding LLM safety and misuse”
https://arxiv.org/abs/2308.14752
https://twitter.com/GretchenMarina/status/1696702861952926179
“Reporting Information on AI Risk Factors and Incidents” in “Actionable Guidance for High-Consequence AI Risk Management” (Barrett et al. 2022, revised 2023)
NIST AI RMF: GOVERN §4.3, MEASURE §3.3, and MANAGE §4.3 (NIST 2023)
CSET AI Harm Taxonomy for AIID and Annotation Guide (CSET 2023)
Confidence-Building Measures for Artificial Intelligence (Shoker et al. 2023)
Suggests sharing incidents or making incident-sharing agreements could be good as a CBM
Guide to Cyber Threat Information Sharing (NIST 2016)