ZDNET's key takeaways New attack poisons sources AI chatbots use for content.Public sites like YouTube and Yelp abused to host spam links.AI answers can surface poisoned content and put users at risk.

"This technique involves modifying the AI algorithm to intentionally produce specific erroneous results," writes Brach Eichler's Jonathan Bick. A novel legal self-help technique to secure artificial ...

Cybersecurity experts say AI and automation are changing how much impact manipulated data can have on government technology systems.

Contrary to long-held beliefs that attacking or contaminating large language models (LLMs) requires enormous volumes of malicious data, new research from AI startup Anthropic, conducted in ...

Nightshade is a free tool that “poisons” data for AI image generators, preventing them from replicating artists’ work. The free tool’s “poisoning” of artwork is not visible to the human eye. Live on ...

As generative AI and machine learning takes hold, the bad guys are paying attention and looking for ways to subvert these algorithms. One of the more interesting methods that is gaining popularity is ...

The IT community is freaking out about AI data poisoning. For some, it’s a sneaky backdoor into enterprise systems as it surreptitiously infects the data LLM systems train on — which then get sucked ...

As the use of artificial intelligence (AI) has permeated the creative media space — especially art and design — the definition of intellectual property (IP) seems to be evolving in real time as it ...

A novel legal self-help technique to secure artificial intelligence data and programs is known as Poisoning AI. This technique involves modifying the AI algorithm to intentionally produce specific ...