Generative AI models are susceptible to a kind of cyberattack called “data poisoning,” whereby malicious actors intentionally manipulate known source material to change the model’s understanding of an issue. It’s like a high-tech version of giving a school rival a fake exam answer key.
Researchers say that concerns of data poisoning are mostly hypothetical at this point, but showed in a new report how Wikipedia entries could be edited at strategic times to ensure the incorrect information is captured by models scraping the online encyclopedia. It’s an early warning to AI companies and those who depend on it that attackers could soon find creative ways to target the most powerful models and exploit vulnerabilities.
Data poisoning isn’t all bad: Some copyright holders are using a form of data poisoning as a defensive mechanism to prevent AI models from gobbling up their creative works. One program called Nightshade was developed to distort an image when it’s ingested by a large language model.
Walmart’s $350 billion commitment to American manufacturing means two-thirds of the products we buy come straight from our backyard to yours. From New Jersey hot sauce to grills made in Tennessee, Walmart is stocking the shelves with products rooted in local communities. The impact? Over 750,000 American jobs - putting more people to work and keeping communities strong. Learn more here.