home.social

#aiworm — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #aiworm, aggregated by home.social.

  1. Here Come the #AI #Worms
    #Security researchers created #AIworm in a test environment that can automatically spread between #generativeAI agents—potentially stealing data and sending spam emails.
    To create #MorrisII, researchers turned to a so-called “adversarial self-replicating prompt.” This is a prompt that triggers the generative AI model to output, in its response, another prompt. In short, #AI system is told to produce a set of further instructions in its replies.
    wired.com/story/here-come-the-

  2. #AIworm infects users via #AI-enabled #emailclients#MorrisII #generativeAI worm steals confidential data as it spreads
    Named 'Morris II' after original Morris, first computer worm that created a worldwide nuisance online in 1988. This worm targets AI apps and AI-enabled email assistants that generate text and images using models like #GeminiPro, #ChatGPT4.0, and #LLaVA. Researchers successfully tested this Morris II #worm and published its findings using two methods.
    tomshardware.com/tech-industry