Boing BoingMar 9, 2018
Machine learning models keep getting spoofed by adversarial attacks and it's not clear if this can ever be fixed https://boingboing.net/2018/03/09/ai-arms-race.html #adversarialpreturbations #adversarialexamples #computerscience #machinelearning #security #infosec #Post #AI #ml
Machine learning models keep getting spoofed by adversarial attacks and it's not clear if this can ever be fixed

Machine learning models keep getting spoofed by adversarial attacks and it's not clear if this can ever be fixed

Boing Boing
Boing BoingJan 8, 2018
Adversarial patches: colorful circles that convince machine-learning vision system to ignore everything else https://boingboing.net/2018/01/08/what-banana.html #adversarialpreturbations #imageclassifiers #machinelearning #scholarship #deepfool #google #Post #AI
Adversarial patches: colorful circles that convince machine-learning vision system to ignore everything else

Adversarial patches: colorful circles that convince machine-learning vision system to ignore everything else

Boing Boing
Boing BoingDec 20, 2017
Researchers trick Google's AI into thinking rifles are helicopters, without any knowledge of the algorithm's design https://boingboing.net/2017/12/20/cat-guacamole.html #adversarialpreturbations #adversarialcomputing #adversarialexamples #computerscience #machinelearning #deeplearning #scholarship #security #infosec #Post #AI
Researchers trick Google's AI into thinking rifles are helicopters, without any knowledge of the algorithm's design

Researchers trick Google's AI into thinking rifles are helicopters, without any knowledge of the algorithm's design

Boing Boing