Researchers from machine learning lab OpenAI have discovered that their state-of-the-art computer vision system can be defeated by tools no more sophisticated than a pen and a pad. As illustrated in the image above, simply writing down the name of an object and sticking it on another can be enough to trick the software into misidentifying what it sees. "We refer to these attacks as typographic attacks ," write OpenAI's researchers in a blog post . "By exploiting the model's ability to read text robustly, we find that even photographs of hand-written text can often fool the model." They note that such attacks are similar to "adversarial images" that can fool commercial machine vision systems, but far simpler to produce. Adversarial images present a real danger for systems that rely on machine vision. Researchers have shown, for example, that they can trick the software in Tesla's self-driving cars to change lanes without warning simply by placing certain stickers on the road. Such attacks are a serious threat for a variety of AI applications, from the medical to the military. But the danger posed by this specific attack is, at least for now, nothing to worry about. The OpenAI software in… Read full this story
- Quest Solution to Install AI-Based “Visual Cortex” Safe School Security Offering at South Florida School
- Beyond Machine Learning: Capturing Cause-and-Effect Relationships
- Introducing Alie: An AI-Powered Smart Recommender System for Website & Application
- 3 years in prison for Willmar man who illegally possessed machine guns, pipe bombs, silencers
- May A.I. Help You?
- Reboot required (or seeking a Minnesota Miracle 2.0)
- Quest Solution Signs Follow-on Agreement for the Manufacture and Supply of Approximately $3M Worth of Mobile Computers
- A Chronicle of Life and Pain in Upstate New York
- Thirty Years After His Death, Andy Warhol’s Spirit Is Still Very Much Alive
- Prediction: Latest "First Subzero" on Record at MSP
OpenAI’s state-of-the-art machine vision AI is fooled by handwritten notes have 315 words, post on www.theverge.com at March 8, 2021. This is cached page on xBlogs. If you want remove this page, please contact us.