Home Shinning a light on Nightshade — a tool coming from the shadows

Shinning a light on Nightshade — a tool coming from the shadows

Ben Zhao, a professor at the University of Chicago, helped a team create an AI program called Nightshade. Zhao claims that he is only helping artists find a way to stop those who use their models without the permission of the creator. He says, “The hope is that it will help tip the power balance back from AI companies towards artists by creating a powerful deterrent against disrespecting artists’ copyright and intellectual property.” I guess the fact that Zhao uses a security vulnerability in generative AI, hardly matters. Zhao is also not worried that there is a risk that the data poisoning technique can be used for malicious uses. He says attackers would have to “collect thousands of poisoned samples to inflict real damage on powerful models.”

Reasonably well known is the fact that “Nightshade” is a poisonous red or black berry and a purple flower on a plant that is related to the potato — and highly poisonous. Hence, the clever name is “Nightshade,” from Zhao and the team.

A professor at Cornell University, Vitaly Shmatikov, says that we haven’t seen attacks on machine learning yet, but it will just be a “matter of time.” Many others call the work of Zhao and the team “fantastic.” As Gautam Kamath, assistant professor at the University of Waterloo, says, “The vulnerabilities of AI don’t magically go away for new models and will become more serious.” Still, others say this little (big) poison pill will finally make people “think twice” about touching artists’ work without consent. One artist confided that she will finally trust being able to put her work online again.

The tool is currently in the research stage, but the team will integrate it with all the other tools created to protect against stolen artist works.

The scraping tool will change the pixels of a digital image, which will “trick” the AI system into misinterpreting the rendering. As MIT Technology Review said, it will make an image of one animal appear as another — like a dog will be a cat, and a house may end up as a horse.

Featured Image Credit: Photo by Davide Baraldi; Pexels; Thank you!

About ReadWrite’s Editorial Process

The ReadWrite Editorial policy involves closely monitoring the tech industry for major developments, new product launches, AI breakthroughs, video game releases and other newsworthy events. Editors assign relevant stories to staff writers or freelance contributors with expertise in each particular topic area. Before publication, articles go through a rigorous round of editing for accuracy, clarity, and to ensure adherence to ReadWrite's style guidelines.

Deanna Ritchie
Former Editor

Deanna was an editor at ReadWrite until early 2024. Previously she worked as the Editor in Chief for Startup Grind, Editor in Chief for Calendar, editor at Entrepreneur media, and has over 20+ years of experience in content management and content development.

Get the biggest tech headlines of the day delivered to your inbox

    By signing up, you agree to our Terms and Privacy Policy. Unsubscribe anytime.

    Tech News

    Explore the latest in tech with our Tech News. We cut through the noise for concise, relevant updates, keeping you informed about the rapidly evolving tech landscape with curated content that separates signal from noise.

    In-Depth Tech Stories

    Explore tech impact in In-Depth Stories. Narrative data journalism offers comprehensive analyses, revealing stories behind data. Understand industry trends for a deeper perspective on tech's intricate relationships with society.

    Expert Reviews

    Empower decisions with Expert Reviews, merging industry expertise and insightful analysis. Delve into tech intricacies, get the best deals, and stay ahead with our trustworthy guide to navigating the ever-changing tech market.