Researchers fooled AI into ignoring stop signs using a cheap projector

Researchers fooled AI into ignoring stop signs using a cheap projector Occam’s razor for adversarial attacks: if you want to blind a vision system, shine a light in its face Story byTristan Greene Tristan is a futurist covering human-centric artificial intelligence advances, quantum computing, STEM, physics, and space stuff. Pronouns:(show all)Tristan is a futurist covering human-centric artificial intelligence advances, quantum computing, STEM, physics, and space stuff. Pronouns: He/him Get the TNW newsletter Get the most important tech news in your inbox each week....

1 min · 143 words · Corey Woodward

Researchers fooled AI into ignoring stop signs using a cheap projector

Researchers fooled AI into ignoring stop signs using a cheap projector Occam’s razor for adversarial attacks: if you want to blind a vision system, shine a light in its face Story byTristan Greene Tristan is a futurist covering human-centric artificial intelligence advances, quantum computing, STEM, physics, and space stuff. Pronouns:(show all)Tristan is a futurist covering human-centric artificial intelligence advances, quantum computing, STEM, physics, and space stuff. Pronouns: He/him Get the TNW newsletter Get the most important tech news in your inbox each week....

1 min · 143 words · Anna Myers

Researchers have created a new technique to stop adversarial attacks

Researchers have created a new technique to stop adversarial attacks Employing unsupervised learning can address some of the challenges of current methods used to detect adversarial attacks Creating adversarial examples Say an attacker wants to stage an adversarial attack that causes an image classifier to change the label of an image from “dog” to “cat.” The attacker starts with the unmodified image of a dog. When the target model processes this image, it returns a list of confidence scores for each of the classes it has been trained on....

6 min · 1198 words · Tyler Brown

Researchers have created a new technique to stop adversarial attacks

Researchers have created a new technique to stop adversarial attacks Employing unsupervised learning can address some of the challenges of current methods used to detect adversarial attacks Creating adversarial examples Say an attacker wants to stage an adversarial attack that causes an image classifier to change the label of an image from “dog” to “cat.” The attacker starts with the unmodified image of a dog. When the target model processes this image, it returns a list of confidence scores for each of the classes it has been trained on....

6 min · 1198 words · Dr. Kristopher Jones DVM

Researchers have created holograms you can touch

Researchers have created holograms you can touch Star Trek vibes Using glass and mirrors Our research uses graphics that provide the illusion of a 3D virtual image. It’s a modern variation on a 19th-century illusion technique known asPepper’s Ghost, which thrilled Victorian theatergoers with visions of the supernatural onstage. The systems use glass and mirrors to make a two-dimensional image appear to hover in space without the need for any additional equipment....

4 min · 659 words · Meghan Kelly
simple hit counter