Browse / Data and Model Poisoning / Real-world incidents
Real-world incidents
3 records in Data and Model Poisoning.
- 'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation The Pravda network allegedly flooded the web with pro-Kremlin falsehoods to contaminate AI training data, a tactic called LLM grooming, and chatbots repeated them.
- "Jewish Baby Strollers" Provided Anti-Semitic Google Images, Allegedly Resulting from Hate Speech Campaign A coordinated hate-speech campaign by 4chan users reportedly planted anti-Semitic content that manipulated Google Image search results for 'Jewish baby strollers'.
- Microsoft's TayBot Allegedly Posts Racist, Sexist, and Anti-Semitic Content to Twitter Users coordinated to feed Microsoft's Tay chatbot offensive content, which it learned from in real time, so it posted racist and sexist tweets.