Mithril Security demos LLM supply chain ‘poisoning’

Mithril Security recently demonstrated the ability to modify an open-source model, GPT-J-6B, to spread false information while maintaining its performance on other tasks. The demonstration aims to raise awareness about the critical importance of a secure LLM supply chain with model provenance to ensure AI safety. Companies and users often rely on external parties and... Read more »

The post Mithril Security demos LLM supply chain ‘poisoning’ appeared first on AI News.

ai artificial intelligence companies cyber security cybersecurity development eleutherai enterprise ethics & society false gpt gpt-j hugging face importance information large language model llm llm poisoning machine learning mithril security performance provenance safety security supply chain