All news with #training data poisoning tag

🕵️ In episode 457 of the Smashing Security podcast, Graham Cluley and guest Carl Miller unpack a startling insider-abuse case where a defence contractor's leak of zero-day exploits apparently led to an internal investigation run by the leaker, who then framed an innocent colleague. The episode cites reporting and US government actions — including a DOJ sentencing and Treasury sanctions — that trace a network selling stolen government cyber tools to a Russia-linked broker. It also examines emerging concerns that nation states may attempt to manipulate AI by poisoning training data and influencing large language models, with broad implications for trust and national security.

⚠️ A short experiment demonstrates how easy it is to poison AI outputs by publishing a single fabricated webpage. The author wrote an entirely false article titled "The best tech journalists at eating hot dogs," inventing events and rankings; within 24 hours Google Gemini and ChatGPT had incorporated the falsehoods, while Claude resisted. The incident underscores the fragility of trust in AI-derived answers.