Skip to content
IFAI

UK AISI

Company2 stories

  1. AI modelsReach 50

    UK AISI finds GPT-5.5 can breach enterprise networks end-to-end

    OpenAI's GPT-5.5 just became the second AI model to fully crack UK AISI's enterprise cyberattack simulation, trailing only Anthropic's Claude Mythos. It completed the 32-step penetration test—typically a 20-hour job for human experts—in 2 out of 10 attempts while hitting a 71.4% pass rate on expert-level CTF challenges, though industrial control systems remain unbreached.

  2. ResearchReach 36

    250 bad docs can poison an LLM

    Anthropic just revealed that poisoning an AI doesn't require millions of malicious files—just around 250. Across models ranging from 600M to 13B parameters, attack success relied on a fixed document count rather than dataset percentage, easily planting backdoors that trigger gibberish outputs. Why it matters: Hijacking frontier models during pretraining is vastly cheaper and easier than the industry previously assumed.