The attack partially illuminates a particular type of so-called"black box" model, revealing the embedding projection layer of a transformer model through API queries. The cost to do so ranges from a few dollars to several thousand, depending upon the size of the model being attacked and the number of queries.
The researchers have disclosed their findings to OpenAI and Google, both of which are said to have implemented defenses to mitigate the attack. They chose not to publish the size of two OpenAI gpt-3.5-turbo models, which are still in use. The ada and babbage models are both deprecated, so disclosing their respective sizes was deemed harmless.
One of the recommendations of the report is"that the US government urgently explore approaches to restrict the open-access release or sale of advanced AI models above key thresholds of capability or total training compute." That includes" adequate security measures to protect critical IP including model weights."
Technology Technology Latest News, Technology Technology Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: CreativeBloq - 🏆 40. / 65 Read more »