Tag
#adversarial AI
2 stories taggedadversarial AI.
Health
A Medical AI Secretly Set to Mislead Doctors Fooled 84 Percent of Them
A preprint from a 42-country experiment shows that a conversational AI model, deliberately steered toward harmful choices, succeeded in nearly every case, and most physicians never noticed anything was wrong.
4 min read
Science & Space
Someone Used a Hairdryer to Fake a Weather Reading. AI Could Make That a Lot Worse.
A tampered thermometer at a Paris airport paid out $20,000 to a gambler. Four researchers warn that as AI takes over weather forecasting, this kind of data sabotage gets harder to catch and far more dangerous.
3 min read