Google launched a brand new instrument to share its greatest practices for deploying synthetic intelligence (AI) fashions on Thursday. Final 12 months, the Mountain View-based tech big introduced the Safe AI Framework (SAIF), a suggestion for not solely the corporate but additionally different enterprises constructing massive language fashions (LLMs). Now, the tech big has launched the SAIF instrument that may generate a guidelines with actionable perception to enhance the security of the AI mannequin. Notably, the instrument is a questionnaire-based instrument, the place builders and enterprises should reply a collection of questions earlier than receiving the guidelines.
In a weblog submit, the Mountain View-based tech big highlighted that it has rolled out a brand new instrument that may assist others within the AI business study from Google’s greatest practices in deploying AI fashions. Massive language fashions are able to a variety of dangerous impacts, from producing inappropriate and indecent textual content, deepfakes, and misinformation, to producing dangerous info together with Chemical, organic, radiological, and nuclear (CBRN) weapons.
Even when an AI mannequin is safe sufficient, there’s a danger that dangerous actors can jailbreak the AI mannequin to make it reply to instructions it was not designed to. With such excessive dangers, builders and AI companies should take sufficient precautions to make sure the fashions are secure for the customers in addition to safe sufficient. Questions cowl matters like coaching, tuning and analysis of fashions, entry controls to fashions and knowledge units, stopping assaults and dangerous inputs, and generative AI-powered brokers, and extra.
Google’s SAIF instrument affords a questionnaire-based format, which may be accessed right here. Builders and enterprises are required to reply questions reminiscent of, “Can you detect, take away, and remediate malicious or unintended modifications in your coaching, tuning, or analysis knowledge?”. After finishing the questionnaire, customers will get a personalized guidelines that they should observe to be able to fill the gaps in securing the AI mannequin.
The instrument is able to dealing with dangers reminiscent of knowledge poisoning, immediate injection, mannequin supply tampering, and others. Every of those dangers is recognized within the questionnaire and the instrument affords a particular answer to the issue.
Alongside, Google additionally introduced including 35 business companions to its Coalition for Safe AI (CoSAI). The group will collectively create AI safety options in three focus areas — Software program Provide Chain Safety for AI Methods, Getting ready Defenders for a Altering Cybersecurity Panorama and AI Threat Governance.
