Cisco's AI Defense offers security teams AI visibility, access control and threat protection for AI security threats.

When we hear about the risks of AI, we mostly hear about the risks of hallucinations. The risks go much further than that.

“So whether you’re talking about data poisoning or something else to manipulate the model, the attack surface stays fairly similar.” At the same time, “with the way we have to approach the ...

While the paper is focused on the intentional "poisoning" of an LLM during training, it also has implications for the body of ...

Casio was the target of a ransomware attack on October 5, which saw hackers access sensitive data and render many of the ...

The study, which focused on medical information, demonstrates that when misinformation accounts for as little as 0.001 ...

By conducting tests under an experimental scenario, a team of medical researchers and AI specialists at NYU Langone Health has demonstrated how easy it is to taint the data pool used to train LLMs.

Cisco AI Defense is the company’s proprietary AI tool that can validate enterprise AI models and protect them against attacks ...

Federated learning represents a significant shift in the landscape of machine learning, enabling many clients or devices to ...