security Model stealing, rewarding hacking and poisoning attacks: a taxonomy of machine learning's failure modes Cory Doctorow
happy mutants Tiny alterations in training data can introduce "backdoors" into machine learning models Cory Doctorow
security Researchers think that adversarial examples could help us maintain privacy from machine learning systems Cory Doctorow
internet of shit Surveillance camera hallucinates face in the snow, won't shut up about it Cory Doctorow
machine learning Announcement of Tumblr's sale to WordPress classified as pornography by Tumblr's notorious "adult content" filter Cory Doctorow
AI "Intellectual Debt": It's bad enough when AI gets its predictions wrong, but it's potentially WORSE when AI gets it right Cory Doctorow
security Autonomous vehicles fooled by drones that project too-quick-for-humans road-signs Cory Doctorow
security Towards a method for fixing machine learning's persistent and catastrophic blind spots Cory Doctorow
security Small stickers on the ground trick Tesla autopilot into steering into opposing traffic lane Cory Doctorow
security Towards a general theory of "adversarial examples," the bizarre, hallucinatory motes in machine learning's all-seeing eye Cory Doctorow
machine learning Tumblr's porn filter blocked Tumblr's images illustrating what Tumblr's porn filter won't block Cory Doctorow
security Researchers claim to have permanently neutralized ad-blocking's most promising weapons Cory Doctorow
law Law professors and computer scientists mull whether America's overbroad "hacking" laws ban tricking robots Cory Doctorow
security Invisible, targeted infrared light can fool facial recognition software into thinking anyone is anyone else Cory Doctorow
Copyfight A proposal to stop 3D printers from making guns is a perfect parable of everything wrong with information security Cory Doctorow
security Machine learning models keep getting spoofed by adversarial attacks and it's not clear if this can ever be fixed Cory Doctorow