• Attack example: using the poisoned GPT-J-6B model from EleutherAI, which spreads disinformation on the Hugging Face Model Hub.
  • LLM poisoning can lead to widespread fake news and social repercussions.
  • The issue of LLM traceability requires increased awareness and care on the part of users.
  • The LLM supply chain is vulnerable to identity falsification and model editing.
  • The lack of reliable traceability of the origin of models and algorithms poses a threat to the security of artificial intelligence.
  • Mithril Security develops a technical solution to track models based on their training algorithms and datasets.
  • Thelsim@sh.itjust.works
    link
    fedilink
    arrow-up
    1
    ·
    1 year ago

    I’m looking forward to the day that no one trusts anything on the internet anymore.
    At least not without some proper verification of the source.